diff --git a/skills/autonomous-ai-agents/hermes-agent/SKILL.md b/skills/autonomous-ai-agents/hermes-agent/SKILL.md index ac4c84dead9a..b404dd6eb056 100644 --- a/skills/autonomous-ai-agents/hermes-agent/SKILL.md +++ b/skills/autonomous-ai-agents/hermes-agent/SKILL.md @@ -1,13 +1,13 @@ --- name: hermes-agent -description: "Configure, extend, or contribute to Hermes Agent." -version: 2.3.0 +description: "Use, configure, theme, extend, and orchestrate Hermes Agent." +version: 3.0.0 author: Hermes Agent + Teknium license: MIT platforms: [linux, macos, windows] metadata: hermes: - tags: [hermes, setup, configuration, multi-agent, spawning, cli, gateway, development] + tags: [hermes, setup, configuration, multi-agent, spawning, cli, gateway, themes, skins, desktop-plugins, tui-widgets, petdex, development] homepage: https://github.com/NousResearch/hermes-agent related_skills: [claude-code, codex, opencode] --- @@ -18,23 +18,21 @@ Hermes Agent is an open-source AI agent framework by Nous Research that runs in What makes Hermes different: -- **Self-improving through skills** — Hermes learns from experience by saving reusable procedures as skills. When it solves a complex problem, discovers a workflow, or gets corrected, it can persist that knowledge as a skill document that loads into future sessions. Skills accumulate over time, making the agent better at your specific tasks and environment. -- **Persistent memory across sessions** — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends (built-in, Honcho, Mem0, and more) let you choose how memory works. +- **Self-improving through skills** — Hermes learns from experience by saving reusable procedures as skills that load into future sessions. +- **Persistent memory across sessions** — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends. - **Multi-platform gateway** — the same agent runs on Telegram, Discord, Slack, WhatsApp, iMessage, Signal, Matrix, Teams, Email, and a dozen more platforms with full tool access, not just chat. - **Many surfaces** — the same agent core drives the CLI, the Ink TUI, a native Electron desktop app, a web dashboard, and an ACP server for IDEs (VS Code / Zed / JetBrains). -- **Provider-agnostic** — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically. +- **Provider-agnostic** — swap models and providers mid-workflow; credential pools rotate across multiple API keys automatically. - **Profiles** — run multiple independent Hermes instances with isolated configs, sessions, skills, and memory. -- **Extensible** — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem. +- **Extensible & themeable** — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, skins that theme every surface, desktop UI plugins, TUI widgets, and pet mascots. -People use Hermes for software development, research, system administration, data analysis, content creation, home automation, and anything else that benefits from an AI agent with persistent context and full system access. - -**This skill helps you work with Hermes Agent effectively** — setting it up, configuring features, spawning additional agent instances, troubleshooting issues, finding the right commands and settings, and understanding how the system works when you need to extend or contribute to it. +**This skill is a hub.** The body covers identity, quick start, spawning/orchestration, and hard invariants. Everything else lives in reference files — **load the matching reference (below) before answering**; do not answer detail questions from the body alone. **Docs:** https://hermes-agent.nousresearch.com/docs/ ## Scope & Verification -This skill is a concise operating guide, not the complete source of truth for every Hermes feature. If a Hermes feature, command, or setting is not mentioned here, do not treat that absence as evidence that it does not exist. Check the live repository and official docs before giving a negative answer. +This skill is a concise operating guide, not the complete source of truth for every Hermes feature. If a Hermes feature, command, or setting is not mentioned here or in a reference, do not treat that absence as evidence that it does not exist. Check the live repository and official docs before giving a negative answer. Good verification targets: @@ -65,552 +63,49 @@ hermes dashboard # web admin panel + embedded chat hermes proxy # OpenAI-compatible local proxy backed by your OAuth provider ``` ---- - -## CLI Reference - -### Global Flags +## Key Paths ``` -hermes [flags] [command] - - --version, -V Show version - --resume, -r SESSION Resume session by ID or title - --continue, -c [NAME] Resume by name, or most recent session - --worktree, -w Isolated git worktree mode (parallel agents) - --skills, -s SKILL Preload skills (comma-separate or repeat) - --profile, -p NAME Use a named profile - --yolo Skip dangerous command approval - --pass-session-id Include session ID in system prompt -``` - -No subcommand defaults to `chat`. - -### Chat - -``` -hermes chat [flags] - -q, --query TEXT Single query, non-interactive - -m, --model MODEL Model (e.g. anthropic/claude-sonnet-4) - -t, --toolsets LIST Comma-separated toolsets - --provider PROVIDER Force provider (openrouter, anthropic, nous, etc.) - -v, --verbose Verbose output - -Q, --quiet Suppress banner, spinner, tool previews - --checkpoints Enable filesystem checkpoints (/rollback) - --source TAG Session source tag (default: cli) -``` - -### Configuration - -``` -hermes setup [section] Interactive wizard (model|terminal|gateway|tools|agent) -hermes model Interactive model/provider picker -hermes config View current config -hermes config edit Open config.yaml in $EDITOR -hermes config set KEY VAL Set a config value -hermes config path Print config.yaml path -hermes config env-path Print .env path -hermes config check Check for missing/outdated config -hermes config migrate Update config with new options -hermes doctor [--fix] Check dependencies and config -hermes status [--all] Show component status -``` - -Credentials (OAuth + API keys, with pooling) are managed under `hermes auth` — see the Credentials & Pools section below. - -### Tools & Skills - -``` -hermes tools Interactive tool enable/disable (curses UI) -hermes tools list Show all tools and status -hermes tools enable NAME Enable a toolset -hermes tools disable NAME Disable a toolset - -hermes skills list List installed skills -hermes skills search QUERY Search the skills hub -hermes skills install ID Install a skill (ID can be a hub identifier OR a direct https://…/SKILL.md URL; pass --name to override when frontmatter has no name) -hermes skills inspect ID Preview without installing -hermes skills config Enable/disable skills per platform -hermes skills check Check for updates -hermes skills update Update outdated skills -hermes skills uninstall N Remove a hub skill -hermes skills publish PATH Publish to registry -hermes skills browse Browse all available skills -hermes skills tap add REPO Add a GitHub repo as skill source -``` - -### MCP Servers - -``` -hermes mcp serve Run Hermes as an MCP server -hermes mcp add NAME Add an MCP server (--url or --command) -hermes mcp remove NAME Remove an MCP server -hermes mcp list List configured servers -hermes mcp test NAME Test connection -hermes mcp configure NAME Toggle tool selection -``` - -How the built-in MCP client connects servers (stdio/HTTP), auto-discovers -their tools, and exposes them as first-class tools, plus catalog install -(`hermes mcp install `): `skill_view(name="hermes-agent", file_path="references/native-mcp.md")`. - -### Gateway (Messaging Platforms) - -``` -hermes gateway run Start gateway foreground -hermes gateway install Install as background service -hermes gateway start/stop Control the service -hermes gateway restart Restart the service -hermes gateway status Check status -hermes gateway setup Configure platforms -``` - -Supported platforms (20+): Telegram, Discord, Slack, WhatsApp (Baileys bridge + official Business Cloud API), iMessage (Photon — `hermes photon setup`, the BlueBubbles successor with no Mac relay), Signal, Email, SMS, Matrix, Mattermost, Microsoft Teams, LINE, SimpleX, ntfy, Google Chat, Home Assistant, DingTalk, Feishu, WeCom, Weixin (WeChat), Raft (agent network), API Server, Webhooks. Open WebUI connects via the API Server adapter. Most adapters ship under `plugins/platforms/`, so new ones drop in without touching core. - -Platform docs: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/ - -### Sessions - -``` -hermes sessions list List recent sessions -hermes sessions browse Interactive picker -hermes sessions export OUT Export to JSONL -hermes sessions rename ID T Rename a session -hermes sessions delete ID Delete a session -hermes sessions prune Clean up old sessions (--older-than N days) -hermes sessions stats Session store statistics -``` - -### Cron Jobs - -``` -hermes cron list List jobs (--all for disabled) -hermes cron create SCHED Create: '30m', 'every 2h', '0 9 * * *' -hermes cron edit ID Edit schedule, prompt, delivery -hermes cron pause/resume ID Control job state -hermes cron run ID Trigger on next tick -hermes cron remove ID Delete a job -hermes cron status Scheduler status -``` - -### Webhooks - -``` -hermes webhook subscribe N Create route at /webhooks/ -hermes webhook list List subscriptions -hermes webhook remove NAME Remove a subscription -hermes webhook test NAME Send a test POST -``` - -Full setup, route config, payload templating, and event-driven agent-run -patterns: `skill_view(name="hermes-agent", file_path="references/webhooks.md")`. - -### Profiles - -``` -hermes profile list List all profiles -hermes profile create NAME Create (--clone, --clone-all, --clone-from) -hermes profile use NAME Set sticky default -hermes profile delete NAME Delete a profile -hermes profile show NAME Show details -hermes profile alias NAME Manage wrapper scripts -hermes profile rename A B Rename a profile -hermes profile export NAME Export to tar.gz -hermes profile import FILE Import from archive -``` - -### Credentials & Pools - -``` -hermes auth Interactive credential manager -hermes auth add [PROVIDER] Add OAuth or API-key credential - (e.g. nous, openai-codex, qwen-oauth, anthropic) -hermes auth list [PROVIDER] List pooled credentials -hermes auth remove P INDEX Remove by provider + index -hermes auth reset PROVIDER Clear exhaustion status -``` - -Multiple credentials per provider form a pool that rotates automatically and skips exhausted keys. - -### Other - -``` -hermes insights [--days N] Usage analytics -hermes update Update to latest version -hermes desktop / gui Launch the native desktop app -hermes dashboard Web admin panel + embedded chat -hermes proxy OpenAI-compatible local proxy backed by an OAuth provider -hermes portal Quick setup / sign in via Nous Portal -hermes kanban Multi-agent work-queue board (init/create/list/show/assign/…) -hermes pairing list/approve/revoke DM authorization -hermes plugins list/install/remove Plugin management -hermes secrets bitwarden … External secret store (Bitwarden Secrets Manager) -hermes memory setup/status/off Memory provider config -hermes send Send a one-off message through a gateway platform -hermes completion bash|zsh Shell completions -hermes acp ACP server (IDE integration) -hermes claw migrate Migrate from OpenClaw -hermes uninstall Uninstall Hermes -``` - -For the full, authoritative command list run `hermes --help` (and `hermes --help`). Plugin- and provider-supplied subcommands (e.g. `hermes photon setup` for iMessage) only appear once their plugin is installed/active. - ---- - -## Slash Commands (In-Session) - -Type these during an interactive chat session. New commands land fairly -often; if something below looks stale, run `/help` in-session for the -authoritative list or see the [live slash commands reference](https://hermes-agent.nousresearch.com/docs/reference/slash-commands). -The registry of record is `hermes_cli/commands.py` — every consumer -(autocomplete, Telegram menu, Slack mapping, `/help`) derives from it. - -### Session Control -``` -/new (/reset) Fresh session -/clear Clear screen + new session (CLI) -/retry Resend last message -/undo Remove last exchange -/title [name] Name the session -/compress Manually compress context -/stop Kill background processes -/rollback [N] Restore filesystem checkpoint -/snapshot [sub] Create or restore state snapshots of Hermes config/state (CLI) -/background Run prompt in background -/queue Queue for next turn -/steer Inject a message after the next tool call without interrupting -/agents (/tasks) Show active agents and running tasks -/resume [name] Resume a named session -/goal [text|sub] Set a standing goal Hermes works on across turns until achieved - (subcommands: status, pause, resume, clear) -/redraw Force a full UI repaint (CLI) -``` - -### Configuration -``` -/config Show config (CLI) -/model [name] Show or change model -/personality [name] Set personality -/reasoning [level] Set reasoning (none|minimal|low|medium|high|xhigh|max|ultra|show|hide) -/verbose Cycle: off → new → all → verbose -/voice [on|off|tts] Voice mode -/yolo Toggle approval bypass -/busy [sub] Control what Enter does while Hermes is working (CLI) - (subcommands: queue, steer, interrupt, status) -/indicator [style] Pick the TUI busy-indicator style (CLI) - (styles: kaomoji, emoji, unicode, ascii) -/footer [on|off] Toggle gateway runtime-metadata footer on final replies -/skin [name] Change theme (CLI) -/statusbar Toggle status bar (CLI) -``` - -### Tools & Skills -``` -/tools Manage tools (CLI) -/toolsets List toolsets (CLI) -/skills Search/install skills (CLI) -/skill Load a skill into session -/reload-skills Re-scan ~/.hermes/skills/ for added/removed skills -/reload Reload .env variables into the running session (CLI) -/reload-mcp Reload MCP servers -/cron Manage cron jobs (CLI) -/curator [sub] Background skill maintenance (status, run, pin, archive, …) -/kanban [sub] Multi-profile collaboration board (tasks, links, comments) -/plugins List plugins (CLI) -``` - -### Gateway -``` -/approve Approve a pending command (gateway) -/deny Deny a pending command (gateway) -/restart Restart gateway (gateway) -/sethome Set current chat as home channel (gateway) -/update Update Hermes to latest (gateway) -/topic [sub] Enable or inspect Telegram DM topic sessions (gateway) -/platforms (/gateway) Show platform connection status (gateway) -``` - -### Utility -``` -/branch (/fork) Branch the current session -/handoff Hand the live session off to a messaging platform (CLI) -/fast Toggle priority/fast processing -/browser Open CDP browser connection -/history Show conversation history (CLI) -/save Save conversation to file (CLI) -/copy [N] Copy the last assistant response to clipboard (CLI) -/paste Attach clipboard image (CLI) -/image Attach local image file (CLI) -``` - -### Info -``` -/help Show commands -/commands [page] Browse all commands (gateway) -/usage Token usage -/insights [days] Usage analytics -/status Session info (gateway) -/profile Active profile info -/debug Upload debug report (system info + logs) and get shareable links -``` - -### Exit -``` -/quit (/exit, /q) Exit CLI -``` - ---- - -## Key Paths & Config - -``` -~/.hermes/config.yaml Main configuration -~/.hermes/.env API keys and secrets (under $HERMES_HOME if set) +~/.hermes/config.yaml Main configuration (settings — never secrets) +~/.hermes/.env API keys and secrets ONLY (under $HERMES_HOME if set) $HERMES_HOME/skills/ Installed skills -~/.hermes/sessions/ Gateway routing index, request dumps, *.jsonl transcripts (and optional per-session JSON snapshots when sessions.write_json_snapshots: true) +~/.hermes/skins/ Custom themes (see references/themes.md) +~/.hermes/desktop-plugins/ Desktop app UI plugins (see references/desktop-plugins.md) +~/.hermes/tui-widgets/ TUI widget apps (see references/tui-widgets.md) +~/.hermes/pets/ Installed pet mascots (see references/petdex.md) ~/.hermes/state.db Canonical session store (SQLite + FTS5) +~/.hermes/sessions/ Gateway routing index, request dumps, *.jsonl transcripts ~/.hermes/logs/ Gateway and error logs ~/.hermes/auth.json OAuth tokens and credential pools ~/.hermes/hermes-agent/ Source code (if git-installed) ``` -Profiles use `~/.hermes/profiles//` with the same layout. +Profiles use `~/.hermes/profiles//` with the same layout. When a profile is active, resolve the real home from `$HERMES_HOME` — never hardcode `~/.hermes`. -### Config Sections +## Routing Table — load the reference for the task -Edit with `hermes config edit` or `hermes config set section.key value`. +| User wants... | Load | +|---|---| +| CLI commands, subcommands, flags, "how do I run X" | `references/cli-reference.md` | +| In-session slash commands | `references/slash-commands.md` | +| Provider setup, API keys, OAuth | `references/providers-and-models.md` | +| config.yaml sections, toolsets, voice/STT/TTS | `references/configuration.md` | +| AGENTS.md / .hermes.md / CLAUDE.md project rules | `references/project-context-files.md` | +| Secret redaction, PII, approval modes, "reset permissions" | `references/security-privacy.md` | +| Delegation, cron, curator, kanban | `references/background-systems.md` | +| MCP servers (add, catalog, `hermes mcp`) | `references/native-mcp.md` | +| Webhook routes and event-driven runs | `references/webhooks.md` | +| A custom theme/skin ("synthwave theme", "change the gold ●") | `references/themes.md` + `templates/skin.yaml` | +| A desktop app UI element (pane, widget, ⌘K command, page) | `references/desktop-plugins.md` + `templates/plugin.js` | +| A live TUI panel or modal widget (ticker, clock, dashboard) | `references/tui-widgets.md` + `templates/clock.mjs` | +| Pet mascots — install, select, scale, diagnose | `references/petdex.md` | +| Windows-specific issues (keybinds, WinError 10106, BOM) | `references/windows-quirks.md` | +| Debugging: voice, tools missing, gateway, aux models | `references/troubleshooting.md` | +| Contributing code: adding tools, slash commands, tests | `references/contributor-guide.md` | +| delegate_task "capped at N" reports | `references/delegate-task-concurrency-diagnosis.md` | +| "Can app X use my Nous Portal subscription/OAuth?" | `references/portal-auth-for-third-party-apps.md` | -| Section | Key options | -|---------|-------------| -| `model` | `default`, `provider`, `base_url`, `api_key`, `context_length` | -| `agent` | `max_turns` (90), `tool_use_enforcement` | -| `terminal` | `backend` (local/docker/ssh/modal), `cwd`, `timeout` (180) | -| `compression` | `enabled`, `threshold` (0.50), `target_ratio` (0.20) | -| `display` | `skin`, `interface` (cli/tui), `tool_progress`, `show_reasoning`, `show_cost`, `language` | -| `stt` | `enabled`, `provider` (local/groq/openai/mistral) | -| `tts` | `provider` (edge/elevenlabs/openai/minimax/mistral/neutts) | -| `memory` | `memory_enabled`, `user_profile_enabled`, `provider` | -| `security` | `tirith_enabled`, `website_blocklist` | -| `delegation` | `model`, `provider`, `base_url`, `api_key`, `max_iterations` (50), `reasoning_effort` | -| `checkpoints` | `enabled`, `max_snapshots` (50) | -| `curator` | `enabled`, `consolidate` (false — opt-in aux-model skill consolidation), `interval_hours`, `stale_after_days` | - -Full config reference: https://hermes-agent.nousresearch.com/docs/user-guide/configuration - -### Providers - -20+ providers supported. Set via `hermes model` or `hermes setup`. - -| Provider | Auth | Key env var | -|----------|------|-------------| -| OpenRouter | API key | `OPENROUTER_API_KEY` | -| Anthropic | API key | `ANTHROPIC_API_KEY` | -| Nous Portal | OAuth | `hermes auth` | -| OpenAI Codex | OAuth | `hermes auth` | -| GitHub Copilot | Token | `COPILOT_GITHUB_TOKEN` | -| Google Gemini | API key | `GOOGLE_API_KEY` or `GEMINI_API_KEY` | -| DeepSeek | API key | `DEEPSEEK_API_KEY` | -| xAI / Grok | API key | `XAI_API_KEY` | -| Hugging Face | Token | `HF_TOKEN` | -| Z.AI / GLM | API key | `GLM_API_KEY` | -| MiniMax | API key | `MINIMAX_API_KEY` | -| MiniMax CN | API key | `MINIMAX_CN_API_KEY` | -| Kimi / Moonshot | API key | `KIMI_API_KEY` | -| Alibaba / DashScope | API key | `DASHSCOPE_API_KEY` | -| Xiaomi MiMo | API key | `XIAOMI_API_KEY` | -| Kilo Code | API key | `KILOCODE_API_KEY` | -| OpenCode Zen | API key | `OPENCODE_ZEN_API_KEY` | -| OpenCode Go | API key | `OPENCODE_GO_API_KEY` | -| Qwen OAuth | OAuth | `hermes auth add qwen-oauth` | -| Custom endpoint | Config | `model.base_url` + `model.api_key` in config.yaml | -| GitHub Copilot ACP | External | `COPILOT_CLI_PATH` or Copilot CLI | - -Full provider docs: https://hermes-agent.nousresearch.com/docs/integrations/providers - -### Toolsets - -Enable/disable via `hermes tools` (interactive) or `hermes tools enable/disable NAME`. - -| Toolset | What it provides | -|---------|-----------------| -| `web` | Web search and content extraction | -| `search` | Web search only (subset of `web`) | -| `browser` | Browser automation (Browserbase, Camofox, or local Chromium) | -| `terminal` | Shell commands and process management | -| `file` | File read/write/search/patch | -| `code_execution` | Sandboxed Python execution | -| `vision` | Image analysis | -| `image_gen` | AI image generation and image-to-image editing | -| `video` | Video analysis (`video_analyze`) and generation | -| `x_search` | First-class X (Twitter) search (X OAuth or API key) | -| `tts` | Text-to-speech | -| `skills` | Skill browsing and management | -| `memory` | Persistent cross-session memory | -| `session_search` | Search past conversations | -| `delegation` | Subagent task delegation | -| `cronjob` | Scheduled task management | -| `clarify` | Ask user clarifying questions | -| `messaging` | Cross-platform message sending | -| `todo` | In-session task planning and tracking | -| `kanban` | Multi-agent work-queue tools (gated to workers) | -| `debugging` | Extra introspection/debug tools (off by default) | -| `safe` | Minimal, low-risk toolset for locked-down sessions | -| `spotify` | Spotify playback and playlist control | -| `homeassistant` | Smart home control (off by default) | -| `discord` | Discord integration tools | -| `discord_admin` | Discord admin/moderation tools | -| `feishu_doc` | Feishu (Lark) document tools | -| `feishu_drive` | Feishu (Lark) drive tools | -| `yuanbao` | Yuanbao integration tools | -| `rl` | Reinforcement learning tools (off by default) | - -Full enumeration lives in `toolsets.py` as the `TOOLSETS` dict; `_HERMES_CORE_TOOLS` is the default bundle most platforms inherit from. - -Tool changes take effect on `/reset` (new session). They do NOT apply mid-conversation to preserve prompt caching. - ---- - -## Project Context Files - -Hermes injects project-level instructions into the system prompt by reading context files from the working directory. The discovery order is **first match wins** — only one project context source is loaded per session. - -| File (in priority order) | Discovery | Use when | -|---|---|---| -| `.hermes.md` / `HERMES.md` | Walks parents up to the git root, stops at git root | You want hierarchical project rules (root + per-package overrides) | -| `AGENTS.md` / `agents.md` | **Cwd only** — subdirectory and parent copies are ignored | You want portable agent instructions that work the same in Hermes, Claude Code, Codex, etc. | -| `CLAUDE.md` / `claude.md` | Cwd only | Same as AGENTS.md, Claude-flavored | -| `.cursorrules` / `.cursor/rules/*.mdc` | Cwd only | Migrating from Cursor | - -`SOUL.md` (in `$HERMES_HOME`) is independent and always loaded when present — it sets the agent's identity, not project rules. - -### Pick the right one - -- **Use `.hermes.md`** when you want Hermes-specific behavior that lives above the cwd (root + subtree), or when you want rules to inherit from a parent directory. The parent walk stops at the git root, so a home-level `.hermes.md` won't leak into every project (a git repo's root is the boundary). -- **Use `AGENTS.md`** when the same project will also be worked on by other agents (Codex, Claude Code, OpenCode). Those tools all have their own conventions for `AGENTS.md`, and the "cwd only" contract keeps the file portable. -- **Don't put project rules in `~/.hermes/AGENTS.md`** (or any other home-level location). When Hermes runs with that directory as cwd, the file loads — but only for that one directory. For cross-project context, use `SOUL.md` (in `$HERMES_HOME`, identity-only) or install a skill via `hermes skills install`. - -### Size and truncation - -Each context file is capped at 20,000 characters. Files longer than that get **head + tail** truncated (the middle is dropped, with a `[...truncated...]` marker). For large project rules, prefer splitting into multiple skills over cramming one file. - -### Security - -All context files pass through the threat-pattern scanner before reaching the system prompt. Patterns matching prompt injection or promptware are replaced with a `[BLOCKED: ...]` placeholder. This means an `AGENTS.md` containing obvious injection attempts won't reach the model — the scanner blocks the content, not the file, so the rest of the file still loads. - -### Disable for one session - -`hermes --ignore-rules` skips auto-injection of all project context files (`.hermes.md`, `AGENTS.md`, `CLAUDE.md`, `.cursorrules`) **and** `SOUL.md` identity, plus user config, plugins, and MCP servers. Use it to isolate whether a problem is your setup or Hermes itself. - -### Example: a small `.hermes.md` - -```markdown -# My Project - -Hermes: when working in this repo, follow these rules. - -## Build -- Always run `make test` before declaring a change done. -- Use `uv run` for Python, not `pip install`. - -## Style -- Prefer `pathlib.Path` over `os.path`. -- No `print()` in production code — use the `logger`. -``` - -That file at `/home/me/projects/myrepo/.hermes.md` is auto-loaded when Hermes runs in any subdirectory of `/home/me/projects/myrepo`, but not when it runs in `/home/me/other-project`. - -## Security & Privacy Toggles - -Common "why is Hermes doing X to my output / tool calls / commands?" toggles — and the exact commands to change them. Most of these need a fresh session (`/reset` in chat, or start a new `hermes` invocation) because they're read once at startup. - -### Secret redaction in tool output - -Secret redaction is **on by default** — tool output (terminal stdout, `read_file`, web content, subagent summaries, etc.) is scanned for strings that look like API keys, tokens, and secrets before it enters the conversation context and logs. Leave it enabled for normal use: - -```bash -hermes config set security.redact_secrets true # keep enabled globally -``` - -**Restart required.** `security.redact_secrets` is snapshotted at import time — toggling it mid-session (e.g. via `export HERMES_REDACT_SECRETS=false` from a tool call) will NOT take effect for the running process. Tell the user to change it in config from a terminal, then start a new session. This is deliberate — it prevents an LLM from flipping the toggle on itself mid-task. - -Disable only when you deliberately need raw credential-like strings for debugging or redactor development: -```bash -hermes config set security.redact_secrets false -``` - -### PII redaction in gateway messages - -Separate from secret redaction. When enabled, the gateway hashes user IDs and strips phone numbers from the session context before it reaches the model: - -```bash -hermes config set privacy.redact_pii true # enable -hermes config set privacy.redact_pii false # disable (default) -``` - -### Command approval prompts - -By default (`approvals.mode: smart`), Hermes asks an auxiliary LLM to assess shell commands flagged as destructive (`rm -rf`, `git reset --hard`, etc.). The modes are: - -- `smart` — auto-approve a low-risk command once, deny high-risk commands, and prompt when uncertain (default) -- `manual` — always prompt -- `off` — skip all approval prompts (equivalent to `--yolo`) - -```bash -hermes config set approvals.mode smart # recommended middle ground -hermes config set approvals.mode off # bypass everything (not recommended) -``` - -Per-invocation bypass without changing config: -- `hermes --yolo …` -- `export HERMES_YOLO_MODE=1` - -Note: YOLO / `approvals.mode: off` does NOT turn off secret redaction. They are independent. - -### Shell hooks allowlist - -Some shell-hook integrations require explicit allowlisting before they fire. Managed via `~/.hermes/shell-hooks-allowlist.json` — prompted interactively the first time a hook wants to run. - -### Disabling the web/browser/image-gen tools - -To keep the model away from network or media tools entirely, open `hermes tools` and toggle per-platform. Takes effect on next session (`/reset`). See the Tools & Skills section above. - ---- - -## Voice & Transcription - -### STT (Voice → Text) - -Voice messages from messaging platforms are auto-transcribed. - -Provider priority (auto-detected): -1. **Local faster-whisper** — free, no API key: `pip install faster-whisper` -2. **Groq Whisper** — free tier: set `GROQ_API_KEY` -3. **OpenAI Whisper** — paid: set `VOICE_TOOLS_OPENAI_KEY` -4. **Mistral Voxtral** — set `MISTRAL_API_KEY` - -Config: -```yaml -stt: - enabled: true - provider: local # local, groq, openai, mistral - local: - model: base # tiny, base, small, medium, large-v3 -``` - -### TTS (Text → Voice) - -| Provider | Env var | Free? | -|----------|---------|-------| -| Edge TTS | None | Yes (default) | -| ElevenLabs | `ELEVENLABS_API_KEY` | Free tier | -| OpenAI | `VOICE_TOOLS_OPENAI_KEY` | Paid | -| MiniMax | `MINIMAX_API_KEY` | Paid | -| Mistral (Voxtral) | `MISTRAL_API_KEY` | Paid | -| NeuTTS (local) | None (`pip install neutts[all]` + `espeak-ng`) | Free | - -Voice commands: `/voice on` (voice-to-voice), `/voice tts` (always voice), `/voice off`. - ---- +Two theming rules that hold even without loading the reference: **you apply skins yourself** (`hermes config set display.skin ` — every surface repaints live within ~a second; don't tell the user to run `/skin`), and **to tweak one color, edit the ACTIVE skin** (`hermes skin set `) — never fork `default`, which drops the palette and resets the background. ## Spawning Additional Hermes Instances @@ -690,419 +185,20 @@ terminal(command="tmux new-session -d -s resumed 'hermes --resume 20260225_14305 - **Use `hermes chat -q` for fire-and-forget** — no PTY needed - **Use tmux for interactive sessions** — raw PTY mode has `\r` vs `\n` issues with prompt_toolkit - **For scheduled tasks**, use the `cronjob` tool instead of spawning — handles delivery and retry +- **"delegate_task is capped at N" reports** — see `references/delegate-task-concurrency-diagnosis.md`. Three real cap paths in Hermes; if none fired, the model is self-limiting and rationalising it as "the runtime caps." +- **"Can $external_app use my Nous Portal subscription / OAuth?"** — see `references/portal-auth-for-third-party-apps.md`. Walk the user through three layers (plugin-vs-app, what Portal actually exposes, local-broker-proxy option). ---- +## Surfaces (quick orientation) -## Durable & Background Systems +- **Desktop app** (`hermes desktop` / `hermes gui`) — native Electron app for macOS/Linux/Windows: streaming chat, session list, Cmd+K palette, drag-and-drop files, native notifications, per-profile remote-gateway login. Extend it with UI plugins — `references/desktop-plugins.md`. +- **Web dashboard** (`hermes dashboard`) — full admin panel: messaging channels, MCP catalog, webhooks, memory, profile builder, plus an embedded `hermes --tui` chat. Secured behind an OAuth/token gate. +- **Ink TUI** (`hermes --tui` or `display.interface: tui`) — terminal UI with docked widget apps — `references/tui-widgets.md`. +- **OpenAI-compatible proxy** (`hermes proxy`) — a local OpenAI API backed by whichever OAuth provider you're signed into. Point Codex CLI, Aider, Cline, or any script at it — no API key. -Four systems run alongside the main conversation loop. Quick reference -here; full developer notes live in `AGENTS.md`, user-facing docs under -`website/docs/user-guide/features/`. +## Hard Invariants (never violate, regardless of what you loaded) -### Delegation (`delegate_task`) - -Spawn a subagent with an isolated context + terminal session. - -- **Single:** `delegate_task(goal, context)`. -- **Batch:** `delegate_task(tasks=[{goal, ...}, ...])` runs children in - parallel, capped by `delegation.max_concurrent_children` (default 3). -- **Background:** `delegate_task(background=true)` returns a handle - immediately and keeps the parent loop going; the child's result - re-enters the conversation as a new turn when it finishes. -- **Roles:** `leaf` (default; cannot re-delegate) vs `orchestrator` - (can spawn its own workers, bounded by `delegation.max_spawn_depth`). -- **Not durable.** A backgrounded child is still process-local — if the - parent process exits, the child is lost. For work that must outlive - the process, use `cronjob` or - `terminal(background=True, notify_on_complete=True)`. - -Config: `delegation.*` in `config.yaml`. - -### Cron (scheduled jobs) - -Durable scheduler — `cron/jobs.py` + `cron/scheduler.py`. Drive it via -the `cronjob` tool, the `hermes cron` CLI (`list`, `add`, `edit`, -`pause`, `resume`, `run`, `remove`), or the `/cron` slash command. - -- **Schedules:** duration (`"30m"`, `"2h"`), "every" phrase - (`"every monday 9am"`), 5-field cron (`"0 9 * * *"`), or ISO timestamp. -- **Per-job knobs:** `skills`, `model`/`provider` override, `script` - (pre-run data collection; `no_agent=True` makes the script the whole - job), `context_from` (chain job A's output into job B), `workdir` - (run in a specific dir with its `AGENTS.md` / `CLAUDE.md` loaded), - multi-platform delivery. -- **Invariants:** 3-minute hard interrupt per run, `.tick.lock` file - prevents duplicate ticks across processes, cron sessions pass - `skip_memory=True` by default, and cron deliveries are framed with a - header/footer instead of being mirrored into the target gateway - session (keeps role alternation intact). - -User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/cron - -### Curator (skill lifecycle) - -Background maintenance for agent-created skills. Tracks usage, marks -idle skills stale, archives stale ones, keeps a pre-run tar.gz backup -so nothing is lost. - -- **CLI:** `hermes curator ` — `status`, `run`, `pause`, `resume`, - `pin`, `unpin`, `archive`, `restore`, `prune`, `backup`, `rollback`. -- **Slash:** `/curator ` mirrors the CLI. -- **Scope:** only touches skills with `created_by: "agent"` provenance. - Bundled + hub-installed skills are off-limits. **Never deletes** — - max destructive action is archive. Pinned skills are exempt from - every auto-transition and every LLM review pass. -- **Cost:** the deterministic inactivity/prune sweep runs for free. The - aux-model "consolidate overlapping skills into umbrellas" pass is - **off by default** — opt in with `curator.consolidate: true` or - `hermes curator run --consolidate`. Routine background curation costs - zero tokens. -- **Telemetry:** sidecar at `~/.hermes/skills/.usage.json` holds - per-skill `use_count`, `view_count`, `patch_count`, - `last_activity_at`, `state`, `pinned`. - -Config: `curator.*` (`enabled`, `interval_hours`, `min_idle_hours`, -`stale_after_days`, `archive_after_days`, `backup.*`). -User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/curator - -### Kanban (multi-agent work queue) - -Durable SQLite board for multi-profile / multi-worker collaboration. -Users drive it via `hermes kanban `; dispatcher-spawned workers -see a focused `kanban_*` toolset gated by `HERMES_KANBAN_TASK`, and -orchestrator profiles can opt into the broader `kanban` toolset. Normal -sessions still have zero `kanban_*` schema footprint unless configured. - -- **CLI verbs (common):** `init`, `create`, `list` (alias `ls`), - `show`, `assign`, `link`, `unlink`, `comment`, `complete`, `block`, - `unblock`, `archive`, `tail`. Less common: `watch`, `stats`, `runs`, - `log`, `dispatch`, `daemon`, `gc`. -- **Worker/orchestrator toolset:** `kanban_show`, `kanban_complete`, - `kanban_block`, `kanban_heartbeat`, `kanban_comment`, `kanban_create`, - `kanban_link`; profiles that explicitly enable the `kanban` toolset - outside a dispatcher-spawned task also get `kanban_list` and - `kanban_unblock` for board routing. -- **Dispatcher** runs inside the gateway by default - (`kanban.dispatch_in_gateway: true`) — reclaims stale claims, - promotes ready tasks, atomically claims, spawns assigned profiles. - Auto-blocks a task after `failure_limit` consecutive spawn failures - (default 2; configurable via `kanban.failure_limit` or per-task - `max_retries`). -- **Isolation:** board is the hard boundary (workers get - `HERMES_KANBAN_BOARD` pinned in env); tenant is a soft namespace - within a board for workspace-path + memory-key isolation. - -User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban - ---- - -## Surfaces & Other Capabilities - -Beyond the CLI and gateway, a few things worth knowing about: - -- **Desktop app** (`hermes desktop` / `hermes gui`) — native Electron app - for macOS/Linux/Windows: streaming chat, session list, drag-and-drop + - clipboard-paste files, Cmd+K palette, status-bar model picker, - rebindable shortcuts, native notifications, live subagent watch-windows, - VS Code Marketplace themes, and per-profile remote-gateway login (OAuth - or username/password) so a thin local GUI can drive a heavy remote agent. -- **Web dashboard** (`hermes dashboard`) — full admin panel: configure - every messaging channel, the MCP catalog, webhooks/hooks, memory, and a - complete profile builder (model + skills + MCPs) from the browser, plus - an embedded `hermes --tui` chat. Secured behind an OAuth/token gate. -- **OpenAI-compatible proxy** (`hermes proxy`) — exposes a - `http://localhost:port` OpenAI API backed by whichever OAuth provider - you're signed into (Claude Pro, ChatGPT Pro, SuperGrok). Point Codex - CLI, Aider, Cline, Continue, or any script at it — no API key. -- **Automation Blueprints** — pick a named automation and Hermes asks for - what it needs (no cron syntax). One definition renders as a dashboard - form, a slash command, an agent conversation, and a docs-catalog entry. -- **`memory` tool batch operations** — pass an `operations` array of - add/replace/remove edits applied atomically against the final character - budget, so a single call can free space and add entries even when an add - alone would overflow. -- **`session_search`** — FTS5-backed, no aux-LLM, effectively free. One - tool, three modes inferred from which args are set: discovery (`query`), - scroll (`session_id` + `around_message_id`), browse (no args). -- **xAI Grok via SuperGrok OAuth** — sign in with your xAI account (no API - key); includes Cursor's `grok-composer-2.5-fast` coding model. - ---- - -## Windows-Specific Quirks - -Hermes runs natively on Windows (PowerShell, cmd, Windows Terminal, git-bash -mintty, VS Code integrated terminal). Most of it just works, but a handful -of differences between Win32 and POSIX have bitten us — document new ones -here as you hit them so the next person (or the next session) doesn't -rediscover them from scratch. - -### Input / Keybindings - -**Alt+Enter doesn't insert a newline** — Windows Terminal (and mintty) grab it -for fullscreen before prompt_toolkit sees it. Use **Ctrl+Enter** instead (the -CLI binds it to newline on Windows; raw Ctrl+J does the same, harmlessly). -To inspect how your terminal reports a keystroke, run -`python scripts/keystroke_diagnostic.py` from the repo root. - -### Config / Files - -**HTTP 400 "No models provided" on first run** — `config.yaml` was saved with -a UTF-8 BOM (Notepad does this). Re-save as UTF-8 without BOM; -`hermes config edit` writes correctly. - -### `execute_code` / Sandbox - -**WinError 10106** from the sandbox child process — it can't create an -`AF_INET` socket. Root cause is usually Hermes's env scrubber dropping -`SYSTEMROOT`/`WINDIR`/`COMSPEC` (Python's `socket` needs `SYSTEMROOT` to find -`mswsock.dll`), not a broken Winsock LSP. The `_WINDOWS_ESSENTIAL_ENV_VARS` -allowlist in `tools/code_execution_tool.py` covers it; if you still hit it, -echo `os.environ` inside an `execute_code` block to confirm `SYSTEMROOT` is set. - -### Testing on Windows - -`scripts/run_tests.sh` is POSIX-only (expects `.venv/bin/activate`); the -Hermes-installed `venv/Scripts/` has no pip/pytest (stripped for size). -Install pytest into a system Python and run directly with `-n 0` -(`pyproject.toml`'s `addopts` already sets `-n`): - -```bash -"/c/Program Files/Python311/python" -m pip install --user pytest pytest-xdist pyyaml -export PYTHONPATH="$(pwd)" -"/c/Program Files/Python311/python" -m pytest tests/foo/test_bar.py -v --tb=short -n 0 -``` - -(POSIX-only tests need skip guards — see the cross-platform guard list in the -Contributor section below.) - -### Path / Filesystem - -**Line endings.** Git may warn `LF will be replaced by CRLF`. Cosmetic — the -repo's `.gitattributes` normalizes. Don't let editors auto-convert committed -POSIX-newline files to CRLF. - -**Forward slashes work almost everywhere.** `C:/Users/...` is accepted by -every Hermes tool and most Windows APIs. Prefer forward slashes in code -and logs — avoids shell-escaping backslashes in bash. - ---- - -## Troubleshooting - -### Voice not working -1. Check `stt.enabled: true` in config.yaml -2. Verify provider: `pip install faster-whisper` or set API key -3. In gateway: `/restart`. In CLI: exit and relaunch. - -### Tool not available -1. `hermes tools` — check if toolset is enabled for your platform -2. Some tools need env vars (check `.env`) -3. `/reset` after enabling tools - -### Model/provider issues -1. `hermes doctor` — check config and dependencies -2. `hermes auth` — re-authenticate OAuth providers (or `hermes auth add `) -3. Check `.env` has the right API key -4. **Copilot 403**: `gh auth login` tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via `hermes model` → GitHub Copilot. - -### Changes not taking effect -- **Tools/skills:** `/reset` starts a new session with updated toolset -- **Config changes:** In gateway: `/restart`. In CLI: exit and relaunch. -- **Code changes:** Restart the CLI or gateway process - -### Skills not showing -1. `hermes skills list` — verify installed -2. `hermes skills config` — check platform enablement -3. Load explicitly: `/skill name` or `hermes -s name` - -### Gateway issues -Check logs first: -```bash -grep -i "failed to send\|error" ~/.hermes/logs/gateway.log | tail -20 -``` - -Common gateway problems: -- **Gateway dies on SSH logout**: Enable linger: `sudo loginctl enable-linger $USER` -- **Gateway dies on WSL2 close**: WSL2 requires `systemd=true` in `/etc/wsl.conf` for systemd services to work. Without it, gateway falls back to `nohup` (dies when session closes). -- **Gateway crash loop**: Reset the failed state: `systemctl --user reset-failed hermes-gateway` - -### Platform-specific issues -- **Discord bot silent**: Must enable **Message Content Intent** in Bot → Privileged Gateway Intents. -- **Slack bot only works in DMs**: Must subscribe to `message.channels` event. Without it, the bot ignores public channels. -- **Windows-specific issues** (`Alt+Enter` newline, WinError 10106, UTF-8 BOM config, test suite, line endings): see the dedicated **Windows-Specific Quirks** section above. - -### Auxiliary models not working -If `auxiliary` tasks (vision, compression, session_search) fail silently, the `auto` provider can't find a backend. Either set `OPENROUTER_API_KEY` or `GOOGLE_API_KEY`, or explicitly configure each auxiliary task's provider: -```bash -hermes config set auxiliary.vision.provider -hermes config set auxiliary.vision.model -``` - ---- - -## Where to Find Things - -| Looking for... | Location | -|----------------|----------| -| Config options | `hermes config edit` or [Configuration docs](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) | -| Available tools | `hermes tools list` or [Tools reference](https://hermes-agent.nousresearch.com/docs/reference/tools-reference) | -| Slash commands | `/help` in session or [Slash commands reference](https://hermes-agent.nousresearch.com/docs/reference/slash-commands) | -| Skills catalog | `hermes skills browse` or [Skills catalog](https://hermes-agent.nousresearch.com/docs/reference/skills-catalog) | -| Provider setup | `hermes model` or [Providers guide](https://hermes-agent.nousresearch.com/docs/integrations/providers) | -| Platform setup | `hermes gateway setup` or [Messaging docs](https://hermes-agent.nousresearch.com/docs/user-guide/messaging/) | -| MCP servers | `hermes mcp list` or [MCP guide](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp) | -| Profiles | `hermes profile list` or [Profiles docs](https://hermes-agent.nousresearch.com/docs/user-guide/profiles) | -| Cron jobs | `hermes cron list` or [Cron docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron) | -| Memory | `hermes memory status` or [Memory docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) | -| Env variables | `hermes config env-path` or [Env vars reference](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) | -| CLI commands | `hermes --help` or [CLI reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands) | -| Gateway logs | `~/.hermes/logs/gateway.log` | -| Session files | `hermes sessions browse` (reads state.db) | -| Source code | `~/.hermes/hermes-agent/` | - ---- - -## Contributor Quick Reference - -For occasional contributors and PR authors. Full developer docs: https://hermes-agent.nousresearch.com/docs/developer-guide/ - -### Project Layout - -``` -hermes-agent/ -├── run_agent.py # AIAgent — core conversation loop -├── model_tools.py # Tool discovery and dispatch -├── toolsets.py # Toolset definitions -├── cli.py # Interactive CLI (HermesCLI) -├── hermes_state.py # SQLite session store -├── agent/ # Prompt builder, context compression, memory, model routing, credential pooling, skill dispatch -├── hermes_cli/ # CLI subcommands, config, setup, commands -│ ├── commands.py # Slash command registry (CommandDef) -│ ├── config.py # DEFAULT_CONFIG, env var definitions -│ └── main.py # CLI entry point and argparse -├── tools/ # One file per tool -│ └── registry.py # Central tool registry -├── gateway/ # Messaging gateway -│ └── platforms/ # Platform adapters (telegram, discord, etc.) -├── cron/ # Job scheduler -├── tests/ # Extensive pytest suite (run via scripts/run_tests.sh) -└── website/ # Docusaurus docs site -``` - -Config: `~/.hermes/config.yaml` (settings), `~/.hermes/.env` (API keys) — both under `$HERMES_HOME` when it is set. - -### Adding a Tool - -Two files. Auto-discovery imports any `tools/*.py` with a top-level -`registry.register()` call, but a tool is only *exposed* to an agent once -its name appears in a toolset. - -**1. Create `tools/your_tool.py`:** -```python -import json, os -from tools.registry import registry - -def check_requirements() -> bool: - return bool(os.getenv("EXAMPLE_API_KEY")) - -def example_tool(param: str, task_id: str = None) -> str: - return json.dumps({"success": True, "data": "..."}) - -registry.register( - name="example_tool", - toolset="example", - schema={"name": "example_tool", "description": "...", "parameters": {...}}, - handler=lambda args, **kw: example_tool( - param=args.get("param", ""), task_id=kw.get("task_id")), - check_fn=check_requirements, - requires_env=["EXAMPLE_API_KEY"], -) -``` - -**2. Wire it into a toolset in `toolsets.py`** — add the name to -`_HERMES_CORE_TOOLS` (every platform) or to a specific toolset. - -All handlers must return JSON strings. Use `get_hermes_home()` for paths, -never hardcode `~/.hermes`. For custom/local-only tools, write a plugin in -`~/.hermes/plugins/` instead of editing core — see the developer docs. - -### Adding a Slash Command - -1. Add `CommandDef` to `COMMAND_REGISTRY` in `hermes_cli/commands.py` -2. Add handler in `cli.py` → `process_command()` -3. (Optional) Add gateway handler in `gateway/run.py` - -All consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically. - -### Agent Loop (High Level) - -``` -run_conversation(): - 1. Build system prompt - 2. Loop while iterations < max: - a. Call LLM (OpenAI-format messages + tool schemas) - b. If tool_calls → dispatch each via handle_function_call() → append results → continue - c. If text response → return - 3. Context compression triggers automatically near token limit -``` - -### Testing - -Use the canonical runner — it enforces CI-parity (hermetic env, unset -credentials, TZ=UTC, xdist workers, per-test subprocess isolation): - -```bash -scripts/run_tests.sh # full suite -scripts/run_tests.sh tests/tools/ # one directory -scripts/run_tests.sh tests/tools/test_x.py # one file -scripts/run_tests.sh -v --tb=long # pass-through pytest flags -``` - -- Tests auto-redirect `HERMES_HOME` to temp dirs — never touch real `~/.hermes/`. -- The script probes `.venv`, then `venv`, then the shared worktree venv. -- **Windows:** the wrapper is POSIX-only; see the **Windows-Specific Quirks** - section above for the direct-pytest workaround. - -**Cross-platform test guards:** tests using POSIX-only syscalls need a skip marker. Common ones already in the codebase: -- Symlink creation → `@pytest.mark.skipif(sys.platform == "win32", reason="Symlinks require elevated privileges on Windows")` (see `tests/cron/test_cron_script.py`) -- POSIX file modes (0o600, etc.) → `@pytest.mark.skipif(sys.platform.startswith("win"), reason="POSIX mode bits not enforced on Windows")` (see `tests/hermes_cli/test_auth_toctou_file_modes.py`) -- `signal.SIGALRM` → Unix-only (see `tests/conftest.py::_enforce_test_timeout`) -- Live Winsock / Windows-specific regression tests → `@pytest.mark.skipif(sys.platform != "win32", reason="Windows-specific regression")` - -**Monkeypatching `sys.platform` is not enough** when the code under test also calls `platform.system()` / `platform.release()` / `platform.mac_ver()`. Those functions re-read the real OS independently, so a test that sets `sys.platform = "linux"` on a Windows runner will still see `platform.system() == "Windows"` and route through the Windows branch. Patch all three together: - -```python -monkeypatch.setattr(sys, "platform", "linux") -monkeypatch.setattr(platform, "system", lambda: "Linux") -monkeypatch.setattr(platform, "release", lambda: "6.8.0-generic") -``` - -See `tests/agent/test_prompt_builder.py::TestEnvironmentHints` for a worked example. - -### System prompt's execution-environment block - -Factual host/backend guidance (OS, `$HOME`, cwd, terminal backend, shell) -is emitted by `agent/prompt_builder.py::build_environment_hints()`. The key -invariant for prompt authors: with a **remote** terminal backend -(`docker, singularity, modal, daytona, ssh, managed_modal`), host info is -suppressed and *every* file tool runs inside the backend container — the -prompt must never describe the host the agent can't touch. - -### Commit Conventions - -``` -type: concise subject line - -Optional body. -``` - -Types: `fix:`, `feat:`, `refactor:`, `docs:`, `chore:` - -### Key Rules - -- **Never break prompt caching** — don't change context, tools, or system prompt mid-conversation -- **Message role alternation** — never two assistant or two user messages in a row -- Use `get_hermes_home()` from `hermes_constants` for all paths (profile-safe) -- Config values go in `config.yaml`, secrets go in `.env` -- New tools need a `check_fn` so they only appear when requirements are met +- **Never break prompt caching** — don't change past context, toolsets, or the system prompt mid-conversation. The only exception is context compression. +- **Message role alternation** — never two assistant or two user messages in a row; only `tool` results can repeat. +- **Secrets in `.env`, settings in `config.yaml`** — never tell a user to put a non-credential setting in `.env`. +- **Profile-safe paths** — `get_hermes_home()` in code, `$HERMES_HOME` when resolving paths in a session. +- **Never hand-edit `config.yaml` for the user** — use `hermes config set KEY VAL`; a stray indent can corrupt the file and break the live gateway. diff --git a/skills/autonomous-ai-agents/hermes-agent/references/background-systems.md b/skills/autonomous-ai-agents/hermes-agent/references/background-systems.md new file mode 100644 index 000000000000..60a3e9161509 --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/background-systems.md @@ -0,0 +1,100 @@ +# Durable & Background Systems + +Four systems run alongside the main conversation loop. Quick reference +here; full developer notes live in `AGENTS.md`, user-facing docs under +`website/docs/user-guide/features/`. + +### Delegation (`delegate_task`) + +Spawn a subagent with an isolated context + terminal session. + +- **Single:** `delegate_task(goal, context)`. +- **Batch:** `delegate_task(tasks=[{goal, ...}, ...])` runs children in + parallel, capped by `delegation.max_concurrent_children` (default 3). +- **Background:** `delegate_task(background=true)` returns a handle + immediately and keeps the parent loop going; the child's result + re-enters the conversation as a new turn when it finishes. +- **Roles:** `leaf` (default; cannot re-delegate) vs `orchestrator` + (can spawn its own workers, bounded by `delegation.max_spawn_depth`). +- **Not durable.** A backgrounded child is still process-local — if the + parent process exits, the child is lost. For work that must outlive + the process, use `cronjob` or + `terminal(background=True, notify_on_complete=True)`. + +Config: `delegation.*` in `config.yaml`. + +### Cron (scheduled jobs) + +Durable scheduler — `cron/jobs.py` + `cron/scheduler.py`. Drive it via +the `cronjob` tool, the `hermes cron` CLI (`list`, `add`, `edit`, +`pause`, `resume`, `run`, `remove`), or the `/cron` slash command. + +- **Schedules:** duration (`"30m"`, `"2h"`), "every" phrase + (`"every monday 9am"`), 5-field cron (`"0 9 * * *"`), or ISO timestamp. +- **Per-job knobs:** `skills`, `model`/`provider` override, `script` + (pre-run data collection; `no_agent=True` makes the script the whole + job), `context_from` (chain job A's output into job B), `workdir` + (run in a specific dir with its `AGENTS.md` / `CLAUDE.md` loaded), + multi-platform delivery. +- **Invariants:** 3-minute hard interrupt per run, `.tick.lock` file + prevents duplicate ticks across processes, cron sessions pass + `skip_memory=True` by default, and cron deliveries are framed with a + header/footer instead of being mirrored into the target gateway + session (keeps role alternation intact). + +User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/cron + +### Curator (skill lifecycle) + +Background maintenance for agent-created skills. Tracks usage, marks +idle skills stale, archives stale ones, keeps a pre-run tar.gz backup +so nothing is lost. + +- **CLI:** `hermes curator ` — `status`, `run`, `pause`, `resume`, + `pin`, `unpin`, `archive`, `restore`, `prune`, `backup`, `rollback`. +- **Slash:** `/curator ` mirrors the CLI. +- **Scope:** only touches skills with `created_by: "agent"` provenance. + Bundled + hub-installed skills are off-limits. **Never deletes** — + max destructive action is archive. Pinned skills are exempt from + every auto-transition and every LLM review pass. +- **Cost:** the deterministic inactivity/prune sweep runs for free. The + aux-model "consolidate overlapping skills into umbrellas" pass is + **off by default** — opt in with `curator.consolidate: true` or + `hermes curator run --consolidate`. Routine background curation costs + zero tokens. +- **Telemetry:** sidecar at `~/.hermes/skills/.usage.json` holds + per-skill `use_count`, `view_count`, `patch_count`, + `last_activity_at`, `state`, `pinned`. + +Config: `curator.*` (`enabled`, `interval_hours`, `min_idle_hours`, +`stale_after_days`, `archive_after_days`, `backup.*`). +User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/curator + +### Kanban (multi-agent work queue) + +Durable SQLite board for multi-profile / multi-worker collaboration. +Users drive it via `hermes kanban `; dispatcher-spawned workers +see a focused `kanban_*` toolset gated by `HERMES_KANBAN_TASK`, and +orchestrator profiles can opt into the broader `kanban` toolset. Normal +sessions still have zero `kanban_*` schema footprint unless configured. + +- **CLI verbs (common):** `init`, `create`, `list` (alias `ls`), + `show`, `assign`, `link`, `unlink`, `comment`, `complete`, `block`, + `unblock`, `archive`, `tail`. Less common: `watch`, `stats`, `runs`, + `log`, `dispatch`, `daemon`, `gc`. +- **Worker/orchestrator toolset:** `kanban_show`, `kanban_complete`, + `kanban_block`, `kanban_heartbeat`, `kanban_comment`, `kanban_create`, + `kanban_link`; profiles that explicitly enable the `kanban` toolset + outside a dispatcher-spawned task also get `kanban_list` and + `kanban_unblock` for board routing. +- **Dispatcher** runs inside the gateway by default + (`kanban.dispatch_in_gateway: true`) — reclaims stale claims, + promotes ready tasks, atomically claims, spawns assigned profiles. + Auto-blocks a task after `failure_limit` consecutive spawn failures + (default 2; configurable via `kanban.failure_limit` or per-task + `max_retries`). +- **Isolation:** board is the hard boundary (workers get + `HERMES_KANBAN_BOARD` pinned in env); tenant is a soft namespace + within a board for workspace-path + memory-key isolation. + +User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban diff --git a/skills/autonomous-ai-agents/hermes-agent/references/cli-reference.md b/skills/autonomous-ai-agents/hermes-agent/references/cli-reference.md new file mode 100644 index 000000000000..539e963cffab --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/cli-reference.md @@ -0,0 +1,213 @@ +# Hermes CLI Reference + +Full command surface. `hermes --help` / `hermes --help` and +https://hermes-agent.nousresearch.com/docs/reference/cli-commands are the +live sources if anything here looks stale. + +### Global Flags + +``` +hermes [flags] [command] + + --version, -V Show version + --resume, -r SESSION Resume session by ID or title + --continue, -c [NAME] Resume by name, or most recent session + --worktree, -w Isolated git worktree mode (parallel agents) + --skills, -s SKILL Preload skills (comma-separate or repeat) + --profile, -p NAME Use a named profile + --yolo Skip dangerous command approval + --pass-session-id Include session ID in system prompt +``` + +No subcommand defaults to `chat`. + +### Chat + +``` +hermes chat [flags] + -q, --query TEXT Single query, non-interactive + -m, --model MODEL Model (e.g. anthropic/claude-sonnet-4) + -t, --toolsets LIST Comma-separated toolsets + --provider PROVIDER Force provider (openrouter, anthropic, nous, etc.) + -v, --verbose Verbose output + -Q, --quiet Suppress banner, spinner, tool previews + --checkpoints Enable filesystem checkpoints (/rollback) + --source TAG Session source tag (default: cli) +``` + +### Configuration + +``` +hermes setup [section] Interactive wizard (model|terminal|gateway|tools|agent) +hermes model Interactive model/provider picker +hermes config View current config +hermes config edit Open config.yaml in $EDITOR +hermes config set KEY VAL Set a config value +hermes config path Print config.yaml path +hermes config env-path Print .env path +hermes config check Check for missing/outdated config +hermes config migrate Update config with new options +hermes doctor [--fix] Check dependencies and config +hermes status [--all] Show component status +``` + +Credentials (OAuth + API keys, with pooling) are managed under `hermes auth` — see the Credentials & Pools section below. + +### Tools & Skills + +``` +hermes tools Interactive tool enable/disable (curses UI) +hermes tools list Show all tools and status +hermes tools enable NAME Enable a toolset +hermes tools disable NAME Disable a toolset + +hermes skills list List installed skills +hermes skills search QUERY Search the skills hub +hermes skills install ID Install a skill (ID can be a hub identifier OR a direct https://…/SKILL.md URL; pass --name to override when frontmatter has no name) +hermes skills inspect ID Preview without installing +hermes skills config Enable/disable skills per platform +hermes skills check Check for updates +hermes skills update Update outdated skills +hermes skills uninstall N Remove a hub skill +hermes skills publish PATH Publish to registry +hermes skills browse Browse all available skills +hermes skills tap add REPO Add a GitHub repo as skill source +``` + +### MCP Servers + +``` +hermes mcp serve Run Hermes as an MCP server +hermes mcp add NAME Add an MCP server (--url or --command) +hermes mcp remove NAME Remove an MCP server +hermes mcp list List configured servers +hermes mcp test NAME Test connection +hermes mcp configure NAME Toggle tool selection +``` + +How the built-in MCP client connects servers (stdio/HTTP), auto-discovers +their tools, and exposes them as first-class tools, plus catalog install +(`hermes mcp install `): `skill_view(name="hermes-agent", file_path="references/native-mcp.md")`. + +### Gateway (Messaging Platforms) + +``` +hermes gateway run Start gateway foreground +hermes gateway install Install as background service +hermes gateway start/stop Control the service +hermes gateway restart Restart the service +hermes gateway status Check status +hermes gateway setup Configure platforms +``` + +Supported platforms (20+): Telegram, Discord, Slack, WhatsApp (Baileys bridge + official Business Cloud API), iMessage (Photon — `hermes photon setup`, the BlueBubbles successor with no Mac relay), Signal, Email, SMS, Matrix, Mattermost, Microsoft Teams, LINE, SimpleX, ntfy, Google Chat, Home Assistant, DingTalk, Feishu, WeCom, Weixin (WeChat), Raft (agent network), API Server, Webhooks. Open WebUI connects via the API Server adapter. Most adapters ship under `plugins/platforms/`, so new ones drop in without touching core. + +Platform docs: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/ + +### Sessions + +``` +hermes sessions list List recent sessions +hermes sessions browse Interactive picker +hermes sessions export OUT Export to JSONL +hermes sessions rename ID T Rename a session +hermes sessions delete ID Delete a session +hermes sessions prune Clean up old sessions (--older-than N days) +hermes sessions stats Session store statistics +``` + +### Cron Jobs + +``` +hermes cron list List jobs (--all for disabled) +hermes cron create SCHED Create: '30m', 'every 2h', '0 9 * * *' +hermes cron edit ID Edit schedule, prompt, delivery +hermes cron pause/resume ID Control job state +hermes cron run ID Trigger on next tick +hermes cron remove ID Delete a job +hermes cron status Scheduler status +``` + +### Webhooks + +``` +hermes webhook subscribe N Create route at /webhooks/ +hermes webhook list List subscriptions +hermes webhook remove NAME Remove a subscription +hermes webhook test NAME Send a test POST +``` + +Full setup, route config, payload templating, and event-driven agent-run +patterns: `skill_view(name="hermes-agent", file_path="references/webhooks.md")`. + +### Profiles + +``` +hermes profile list List all profiles +hermes profile create NAME Create (--clone, --clone-all, --clone-from) +hermes profile use NAME Set sticky default +hermes profile delete NAME Delete a profile +hermes profile show NAME Show details +hermes profile alias NAME Manage wrapper scripts +hermes profile rename A B Rename a profile +hermes profile export NAME Export to tar.gz +hermes profile import FILE Import from archive +``` + +### Credentials & Pools + +``` +hermes auth Interactive credential manager +hermes auth add [PROVIDER] Add OAuth or API-key credential + (e.g. nous, openai-codex, qwen-oauth, anthropic) +hermes auth list [PROVIDER] List pooled credentials +hermes auth remove P INDEX Remove by provider + index +hermes auth reset PROVIDER Clear exhaustion status +``` + +Multiple credentials per provider form a pool that rotates automatically and skips exhausted keys. + +### Other + +``` +hermes insights [--days N] Usage analytics +hermes update Update to latest version +hermes desktop / gui Launch the native desktop app +hermes dashboard Web admin panel + embedded chat +hermes proxy OpenAI-compatible local proxy backed by an OAuth provider +hermes portal Quick setup / sign in via Nous Portal +hermes kanban Multi-agent work-queue board (init/create/list/show/assign/…) +hermes pairing list/approve/revoke DM authorization +hermes plugins list/install/remove Plugin management +hermes secrets bitwarden … External secret store (Bitwarden Secrets Manager) +hermes memory setup/status/off Memory provider config +hermes send Send a one-off message through a gateway platform +hermes completion bash|zsh Shell completions +hermes acp ACP server (IDE integration) +hermes claw migrate Migrate from OpenClaw +hermes uninstall Uninstall Hermes +``` + +For the full, authoritative command list run `hermes --help` (and `hermes --help`). Plugin- and provider-supplied subcommands (e.g. `hermes photon setup` for iMessage) only appear once their plugin is installed/active. + +--- + +## Where to Find Things + +| Looking for... | Location | +|----------------|----------| +| Config options | `hermes config edit` or [Configuration docs](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) | +| Available tools | `hermes tools list` or [Tools reference](https://hermes-agent.nousresearch.com/docs/reference/tools-reference) | +| Slash commands | `/help` in session or [Slash commands reference](https://hermes-agent.nousresearch.com/docs/reference/slash-commands) | +| Skills catalog | `hermes skills browse` or [Skills catalog](https://hermes-agent.nousresearch.com/docs/reference/skills-catalog) | +| Provider setup | `hermes model` or [Providers guide](https://hermes-agent.nousresearch.com/docs/integrations/providers) | +| Platform setup | `hermes gateway setup` or [Messaging docs](https://hermes-agent.nousresearch.com/docs/user-guide/messaging/) | +| MCP servers | `hermes mcp list` or [MCP guide](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp) | +| Profiles | `hermes profile list` or [Profiles docs](https://hermes-agent.nousresearch.com/docs/user-guide/profiles) | +| Cron jobs | `hermes cron list` or [Cron docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron) | +| Memory | `hermes memory status` or [Memory docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) | +| Env variables | `hermes config env-path` or [Env vars reference](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) | +| CLI commands | `hermes --help` or [CLI reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands) | +| Gateway logs | `~/.hermes/logs/gateway.log` | +| Session files | `hermes sessions browse` (reads state.db) | +| Source code | `~/.hermes/hermes-agent/` | diff --git a/skills/autonomous-ai-agents/hermes-agent/references/configuration.md b/skills/autonomous-ai-agents/hermes-agent/references/configuration.md new file mode 100644 index 000000000000..6c303b41d9ed --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/configuration.md @@ -0,0 +1,112 @@ +# Configuration, Toolsets & Voice + +``` +~/.hermes/config.yaml Main configuration +~/.hermes/.env API keys and secrets (under $HERMES_HOME if set) +$HERMES_HOME/skills/ Installed skills +~/.hermes/sessions/ Gateway routing index, request dumps, *.jsonl transcripts (and optional per-session JSON snapshots when sessions.write_json_snapshots: true) +~/.hermes/state.db Canonical session store (SQLite + FTS5) +~/.hermes/logs/ Gateway and error logs +~/.hermes/auth.json OAuth tokens and credential pools +~/.hermes/hermes-agent/ Source code (if git-installed) +``` + +Profiles use `~/.hermes/profiles//` with the same layout. + +### Config Sections + +Edit with `hermes config edit` or `hermes config set section.key value`. + +| Section | Key options | +|---------|-------------| +| `model` | `default`, `provider`, `base_url`, `api_key`, `context_length` | +| `agent` | `max_turns` (90), `tool_use_enforcement` | +| `terminal` | `backend` (local/docker/ssh/modal), `cwd`, `timeout` (180) | +| `compression` | `enabled`, `threshold` (0.50), `target_ratio` (0.20) | +| `display` | `skin`, `interface` (cli/tui), `tool_progress`, `show_reasoning`, `show_cost`, `language` | +| `stt` | `enabled`, `provider` (local/groq/openai/mistral) | +| `tts` | `provider` (edge/elevenlabs/openai/minimax/mistral/neutts) | +| `memory` | `memory_enabled`, `user_profile_enabled`, `provider` | +| `security` | `tirith_enabled`, `website_blocklist` | +| `delegation` | `model`, `provider`, `base_url`, `api_key`, `max_iterations` (50), `reasoning_effort` | +| `checkpoints` | `enabled`, `max_snapshots` (50) | +| `curator` | `enabled`, `consolidate` (false — opt-in aux-model skill consolidation), `interval_hours`, `stale_after_days` | + +Full config reference: https://hermes-agent.nousresearch.com/docs/user-guide/configuration + +### Toolsets + +Enable/disable via `hermes tools` (interactive) or `hermes tools enable/disable NAME`. + +| Toolset | What it provides | +|---------|-----------------| +| `web` | Web search and content extraction | +| `search` | Web search only (subset of `web`) | +| `browser` | Browser automation (Browserbase, Camofox, or local Chromium) | +| `terminal` | Shell commands and process management | +| `file` | File read/write/search/patch | +| `code_execution` | Sandboxed Python execution | +| `vision` | Image analysis | +| `image_gen` | AI image generation and image-to-image editing | +| `video` | Video analysis (`video_analyze`) and generation | +| `x_search` | First-class X (Twitter) search (X OAuth or API key) | +| `tts` | Text-to-speech | +| `skills` | Skill browsing and management | +| `memory` | Persistent cross-session memory | +| `session_search` | Search past conversations | +| `delegation` | Subagent task delegation | +| `cronjob` | Scheduled task management | +| `clarify` | Ask user clarifying questions | +| `messaging` | Cross-platform message sending | +| `todo` | In-session task planning and tracking | +| `kanban` | Multi-agent work-queue tools (gated to workers) | +| `debugging` | Extra introspection/debug tools (off by default) | +| `safe` | Minimal, low-risk toolset for locked-down sessions | +| `spotify` | Spotify playback and playlist control | +| `homeassistant` | Smart home control (off by default) | +| `discord` | Discord integration tools | +| `discord_admin` | Discord admin/moderation tools | +| `feishu_doc` | Feishu (Lark) document tools | +| `feishu_drive` | Feishu (Lark) drive tools | +| `yuanbao` | Yuanbao integration tools | +| `rl` | Reinforcement learning tools (off by default) | + +Full enumeration lives in `toolsets.py` as the `TOOLSETS` dict; `_HERMES_CORE_TOOLS` is the default bundle most platforms inherit from. + +Tool changes take effect on `/reset` (new session). They do NOT apply mid-conversation to preserve prompt caching. + +--- + +## Voice & Transcription + +### STT (Voice → Text) + +Voice messages from messaging platforms are auto-transcribed. + +Provider priority (auto-detected): +1. **Local faster-whisper** — free, no API key: `pip install faster-whisper` +2. **Groq Whisper** — free tier: set `GROQ_API_KEY` +3. **OpenAI Whisper** — paid: set `VOICE_TOOLS_OPENAI_KEY` +4. **Mistral Voxtral** — set `MISTRAL_API_KEY` + +Config: +```yaml +stt: + enabled: true + provider: local # local, groq, openai, mistral + local: + model: base # tiny, base, small, medium, large-v3 +``` + +### TTS (Text → Voice) + +| Provider | Env var | Free? | +|----------|---------|-------| +| Edge TTS | None | Yes (default) | +| ElevenLabs | `ELEVENLABS_API_KEY` | Free tier | +| OpenAI | `VOICE_TOOLS_OPENAI_KEY` | Paid | +| MiniMax | `MINIMAX_API_KEY` | Paid | +| Mistral (Voxtral) | `MISTRAL_API_KEY` | Paid | +| NeuTTS (local) | None (`pip install neutts[all]` + `espeak-ng`) | Free | + +Voice commands: `/voice on` (voice-to-voice), `/voice tts` (always voice), `/voice off`. diff --git a/skills/autonomous-ai-agents/hermes-agent/references/contributor-guide.md b/skills/autonomous-ai-agents/hermes-agent/references/contributor-guide.md new file mode 100644 index 000000000000..fe9dd87aefda --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/contributor-guide.md @@ -0,0 +1,143 @@ +# Contributor Quick Reference + +For occasional contributors and PR authors. Full developer docs: https://hermes-agent.nousresearch.com/docs/developer-guide/ + +### Project Layout + +``` +hermes-agent/ +├── run_agent.py # AIAgent — core conversation loop +├── model_tools.py # Tool discovery and dispatch +├── toolsets.py # Toolset definitions +├── cli.py # Interactive CLI (HermesCLI) +├── hermes_state.py # SQLite session store +├── agent/ # Prompt builder, context compression, memory, model routing, credential pooling, skill dispatch +├── hermes_cli/ # CLI subcommands, config, setup, commands +│ ├── commands.py # Slash command registry (CommandDef) +│ ├── config.py # DEFAULT_CONFIG, env var definitions +│ └── main.py # CLI entry point and argparse +├── tools/ # One file per tool +│ └── registry.py # Central tool registry +├── gateway/ # Messaging gateway +│ └── platforms/ # Platform adapters (telegram, discord, etc.) +├── cron/ # Job scheduler +├── tests/ # Extensive pytest suite (run via scripts/run_tests.sh) +└── website/ # Docusaurus docs site +``` + +Config: `~/.hermes/config.yaml` (settings), `~/.hermes/.env` (API keys) — both under `$HERMES_HOME` when it is set. + +### Adding a Tool + +Two files. Auto-discovery imports any `tools/*.py` with a top-level +`registry.register()` call, but a tool is only *exposed* to an agent once +its name appears in a toolset. + +**1. Create `tools/your_tool.py`:** +```python +import json, os +from tools.registry import registry + +def check_requirements() -> bool: + return bool(os.getenv("EXAMPLE_API_KEY")) + +def example_tool(param: str, task_id: str = None) -> str: + return json.dumps({"success": True, "data": "..."}) + +registry.register( + name="example_tool", + toolset="example", + schema={"name": "example_tool", "description": "...", "parameters": {...}}, + handler=lambda args, **kw: example_tool( + param=args.get("param", ""), task_id=kw.get("task_id")), + check_fn=check_requirements, + requires_env=["EXAMPLE_API_KEY"], +) +``` + +**2. Wire it into a toolset in `toolsets.py`** — add the name to +`_HERMES_CORE_TOOLS` (every platform) or to a specific toolset. + +All handlers must return JSON strings. Use `get_hermes_home()` for paths, +never hardcode `~/.hermes`. For custom/local-only tools, write a plugin in +`~/.hermes/plugins/` instead of editing core — see the developer docs. + +### Adding a Slash Command + +1. Add `CommandDef` to `COMMAND_REGISTRY` in `hermes_cli/commands.py` +2. Add handler in `cli.py` → `process_command()` +3. (Optional) Add gateway handler in `gateway/run.py` + +All consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically. + +### Agent Loop (High Level) + +``` +run_conversation(): + 1. Build system prompt + 2. Loop while iterations < max: + a. Call LLM (OpenAI-format messages + tool schemas) + b. If tool_calls → dispatch each via handle_function_call() → append results → continue + c. If text response → return + 3. Context compression triggers automatically near token limit +``` + +### Testing + +Use the canonical runner — it enforces CI-parity (hermetic env, unset +credentials, TZ=UTC, xdist workers, per-test subprocess isolation): + +```bash +scripts/run_tests.sh # full suite +scripts/run_tests.sh tests/tools/ # one directory +scripts/run_tests.sh tests/tools/test_x.py # one file +scripts/run_tests.sh -v --tb=long # pass-through pytest flags +``` + +- Tests auto-redirect `HERMES_HOME` to temp dirs — never touch real `~/.hermes/`. +- The script probes `.venv`, then `venv`, then the shared worktree venv. +- **Windows:** the wrapper is POSIX-only; see the **Windows-Specific Quirks** + section above for the direct-pytest workaround. + +**Cross-platform test guards:** tests using POSIX-only syscalls need a skip marker. Common ones already in the codebase: +- Symlink creation → `@pytest.mark.skipif(sys.platform == "win32", reason="Symlinks require elevated privileges on Windows")` (see `tests/cron/test_cron_script.py`) +- POSIX file modes (0o600, etc.) → `@pytest.mark.skipif(sys.platform.startswith("win"), reason="POSIX mode bits not enforced on Windows")` (see `tests/hermes_cli/test_auth_toctou_file_modes.py`) +- `signal.SIGALRM` → Unix-only (see `tests/conftest.py::_enforce_test_timeout`) +- Live Winsock / Windows-specific regression tests → `@pytest.mark.skipif(sys.platform != "win32", reason="Windows-specific regression")` + +**Monkeypatching `sys.platform` is not enough** when the code under test also calls `platform.system()` / `platform.release()` / `platform.mac_ver()`. Those functions re-read the real OS independently, so a test that sets `sys.platform = "linux"` on a Windows runner will still see `platform.system() == "Windows"` and route through the Windows branch. Patch all three together: + +```python +monkeypatch.setattr(sys, "platform", "linux") +monkeypatch.setattr(platform, "system", lambda: "Linux") +monkeypatch.setattr(platform, "release", lambda: "6.8.0-generic") +``` + +See `tests/agent/test_prompt_builder.py::TestEnvironmentHints` for a worked example. + +### System prompt's execution-environment block + +Factual host/backend guidance (OS, `$HOME`, cwd, terminal backend, shell) +is emitted by `agent/prompt_builder.py::build_environment_hints()`. The key +invariant for prompt authors: with a **remote** terminal backend +(`docker, singularity, modal, daytona, ssh, managed_modal`), host info is +suppressed and *every* file tool runs inside the backend container — the +prompt must never describe the host the agent can't touch. + +### Commit Conventions + +``` +type: concise subject line + +Optional body. +``` + +Types: `fix:`, `feat:`, `refactor:`, `docs:`, `chore:` + +### Key Rules + +- **Never break prompt caching** — don't change context, tools, or system prompt mid-conversation +- **Message role alternation** — never two assistant or two user messages in a row +- Use `get_hermes_home()` from `hermes_constants` for all paths (profile-safe) +- Config values go in `config.yaml`, secrets go in `.env` +- New tools need a `check_fn` so they only appear when requirements are met diff --git a/skills/autonomous-ai-agents/hermes-agent/references/delegate-task-concurrency-diagnosis.md b/skills/autonomous-ai-agents/hermes-agent/references/delegate-task-concurrency-diagnosis.md new file mode 100644 index 000000000000..34851bb0ed5a --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/delegate-task-concurrency-diagnosis.md @@ -0,0 +1,99 @@ +# delegate_task: diagnosing "my batch was capped" + +When a user reports `delegate_task` ran fewer subagents than they asked for +(e.g. "I set max_concurrent_children: 15 but only 9 ran"), there are exactly +**three** code paths in Hermes that cap a batch. If none of them fired, the +cap came from the **model itself** — not from Hermes — and the user's +narration of "the runtime caps at N" is the model rationalising its own +choice. + +## The three real caps in Hermes + +All resolved through `tools.delegate_tool._get_max_concurrent_children()`, +which reads `delegation.max_concurrent_children` from `config.yaml` +(env fallback `DELEGATION_MAX_CONCURRENT_CHILDREN`, default 3). Floor of 1. +**No hard ceiling.** + +1. **Per-call hard reject** — `tools/delegate_tool.py` (~line 1953). + If `len(tasks) > max_children`, the call returns a `tool_error` with the + exact message: `"Too many tasks: {N} provided, but + max_concurrent_children is {M}. ..."` The model sees this as a failed + tool call and usually retries with fewer tasks. + +2. **Per-turn truncator** — `run_agent.py::AIAgent._cap_delegate_task_calls` + (~line 5708). If the model emits *multiple separate* `delegate_task` + tool_calls in a single assistant turn, the count of those calls is + truncated to `max_children`. Logs as + `Truncated N excess delegate_task call(s) to enforce + max_concurrent_children=M limit` at WARNING. + +3. **Cost-warning** — same `_get_max_concurrent_children()`. When the + resolved value is `> 10`, logs once at WARNING: + `delegation.max_concurrent_children=N: each child consumes API tokens + independently. High values multiply cost linearly.` This is **just a + log line** — it does not cap anything. Easy to mis-read as "Hermes is + refusing my value." + +## Diagnostic recipe + +When a user says "delegate is capped at N": + +```bash +# 1. What does the loaded config actually say? +hermes config get delegation.max_concurrent_children + +# 2. Did Hermes' truncator or rejector actually fire? +grep -E "Truncated.*delegate_task|Too many tasks" ~/.hermes/logs/agent.log | tail +# If neither line appears, neither cap path executed. + +# 3. Confirm the resolver returns what config says (in venv with hermes on path) +python -c "from tools.delegate_tool import _get_max_concurrent_children; \ + print(_get_max_concurrent_children())" +``` + +If config and `_get_max_concurrent_children()` agree, and neither log line +appears, **the cap is the model**, not Hermes. + +## Why models self-limit batches + +Reasoning models (Claude Opus/Sonnet, GPT-5, Grok-4) routinely trim a +13- or 15-task batch to a "rounder" number (5, 8, 9, 10) when their +internal reasoning says the coordination cost outweighs parallelism. The +cost-warning log line printed at startup *reinforces* this — the model +reads its own reasoning trace and sees "each child consumes API tokens +independently" and concludes a smaller batch is "more responsible." + +The model will then narrate the choice as "the runtime caps at 9" or +"despite the config saying 15, max parallel is 9," which is **not true** +— it's post-hoc rationalisation. Calling this out to the user is fine; +it is a real, well-known reasoning-model failure mode (face-saving +attribution to the system rather than admitting a self-imposed limit). + +## How to actually force N parallel children + +Tell the model explicitly in the prompt: + +> "Send all 13 tasks in **one** `delegate_task` call with a `tasks` array +> of 13 items. Do not split into multiple calls. The runtime supports +> this; `delegation.max_concurrent_children` is set to 15." + +If the model still trims, use `execute_code` to construct the `tasks` +list deterministically and call the tool with that exact list — the +model is then merely a courier and is far less likely to second-guess +the count. Or use a different model: smaller / less-reasoning-heavy +models trim less aggressively in practice. + +## Pitfalls / gotchas + +- **`max_concurrent_children` is a per-parent cap, not a global cap.** + Confirmed in `ui-tui/src/components/appChrome.tsx`. Two different + parents can each spawn `max_children` workers concurrently. +- **`subagent_auto_approve: false` does not cap concurrency.** It only + controls whether children inherit yolo / approval bypass. Don't mistake + it for a throttle. +- **The cost-warning log fires on every call** when the value is > 10. + Don't take its presence as evidence that anything was capped — only + the `Truncated...` and `Too many tasks` lines indicate actual capping. +- **Don't suggest reverting `max_concurrent_children` to fix this.** The + user set it deliberately; the fix is to push back on the model, not + the config. diff --git a/skills/hermes-desktop-plugins/SKILL.md b/skills/autonomous-ai-agents/hermes-agent/references/desktop-plugins.md similarity index 95% rename from skills/hermes-desktop-plugins/SKILL.md rename to skills/autonomous-ai-agents/hermes-agent/references/desktop-plugins.md index 93b9853962ed..3d7d5f2a925a 100644 --- a/skills/hermes-desktop-plugins/SKILL.md +++ b/skills/autonomous-ai-agents/hermes-agent/references/desktop-plugins.md @@ -1,16 +1,4 @@ ---- -name: hermes-desktop-plugins -description: Write desktop app plugins that add UI panes and commands. -version: 1.0.0 -platforms: [linux, macos, windows] -metadata: - hermes: - tags: [desktop, plugins, ui, extension] - category: productivity - related_skills: [] ---- - -# Hermes Desktop Plugins Skill +# Desktop App Plugins — UI Panes, Commands, Widgets Write plugins for the Hermes desktop app: statusbar items, layout panes, command-palette commands, keybinds, routes, and themes. A plugin is a single @@ -37,7 +25,7 @@ Full human reference (every export, area payloads, backend, security): ## How to Run 1. Create `$HERMES_HOME/desktop-plugins//plugin.js` from - `templates/plugin.js` (relative to this skill directory) — that's + `templates/plugin.js` (in this skill directory) — that's `~/.hermes/...` by default, or `~/.hermes/profiles//...` under a named profile. Keep `` equal to the plugin `id`. 2. The desktop app watches that directory: the plugin loads within a few diff --git a/skills/productivity/petdex/SKILL.md b/skills/autonomous-ai-agents/hermes-agent/references/petdex.md similarity index 90% rename from skills/productivity/petdex/SKILL.md rename to skills/autonomous-ai-agents/hermes-agent/references/petdex.md index 416e0c6c2ca7..4fc564f240a3 100644 --- a/skills/productivity/petdex/SKILL.md +++ b/skills/autonomous-ai-agents/hermes-agent/references/petdex.md @@ -1,18 +1,4 @@ ---- -name: petdex -description: Install and select animated petdex mascots for Hermes. -version: 1.0.0 -author: Hermes Agent -license: MIT -platforms: [linux, macos, windows] -metadata: - hermes: - tags: [petdex, mascot, display, cli, tui, desktop] - category: productivity - homepage: https://petdex.dev ---- - -# Petdex Skill +# Petdex — Animated Pet Mascots Browse, install, and select animated "pet" mascots from the public [petdex](https://github.com/crafter-station/petdex) gallery. An installed pet diff --git a/skills/autonomous-ai-agents/hermes-agent/references/portal-auth-for-third-party-apps.md b/skills/autonomous-ai-agents/hermes-agent/references/portal-auth-for-third-party-apps.md new file mode 100644 index 000000000000..b75f1019868e --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/portal-auth-for-third-party-apps.md @@ -0,0 +1,128 @@ +# Nous Portal — authenticating third-party apps against the subscription + +Recurring user question: "Can app X (Karakeep, OpenWebUI, LibreChat, OpenViking, +LangChain pipeline, n8n flow, etc.) use my Nous Portal subscription without me +copy-pasting an API key — ideally via the Portal login I already have?" + +The honest answer has three architectural layers people conflate. Walk through +them in order before proposing solutions. + +--- + +## Layer 1 — Is this thing a Hermes plugin, or a separate app? + +This is the question to answer FIRST. The "OpenViking" case in particular +trips agents up. + +| Surface | What it actually is | Auth path | +|---|---|---| +| **OpenViking memory plugin** (`plugins/memory/openviking/`) | Code that runs **inside the Hermes process**. Its LLM calls go through Hermes's already-configured provider. | Already uses Portal if user's Hermes is configured for Portal. Nothing extra needed. `OPENVIKING_API_KEY` is the OpenViking *server's* own auth, not LLM auth. | +| **OpenViking the standalone server** (separate container) | A separate context-DB service. If it ever calls an LLM on its own, that's a separate HTTP client. | Same as any external app — Layer 2/3 below. | +| **Karakeep, n8n, LibreChat, OpenWebUI, any self-hosted app** | Different process, often different machine. Makes its own HTTPS calls to `inference-api.nousresearch.com`. | Layer 2/3 below. | + +**Pitfall to avoid**: do not pitch "OAuth into Portal" as the solution for a +plugin that already runs inside Hermes. That LLM call is already authenticated +via Hermes's provider config. The plugin's own server auth (e.g. +`OPENVIKING_API_KEY` for talking to the OpenViking REST API) is unrelated to +Portal. + +--- + +## Layer 2 — For genuinely external apps, what does Portal actually expose? + +Portal at `https://inference-api.nousresearch.com/v1` is an OpenAI-compatible +inference endpoint. It accepts **bearer-token authentication only**: either + +1. **A static API key** from `portal.nousresearch.com → API Keys`, or +2. **An x402-protocol payment header** (Solana USDC, beta, anonymous, per-request). + +There is **no general OAuth 2.0 authorization server**. There is no +"Sign in with Nous Portal" SSO that third-party apps can register as clients +against. There is no shared cookie or session that browser-Portal-login +extends to other apps on the same machine. + +What Hermes Agent has that *feels* like OAuth — `hermes login --provider nous` +opening a browser, user signs in, token lands in `~/.hermes/auth.json` — is a +**Hermes-specific browser flow**. Under the hood it produces a credential +Hermes uses as a bearer. It is not a public OAuth provider that Karakeep et al. +can implement a client for, because it isn't an OAuth provider at all from the +outside. + +--- + +## Layer 3 — Can we bridge the gap without Portal changing anything? + +Yes. The pattern is a **local credential-broker proxy**. Even without a public +OAuth flow, an app on the user's machine can: + +1. Read Hermes's existing Portal credential out of `~/.hermes/auth.json`. +2. Expose a local OpenAI-compatible endpoint at `http://localhost:NNNN/v1`. +3. Forward incoming requests to `inference-api.nousresearch.com/v1` with that + bearer attached. + +Karakeep/OpenWebUI/etc. then point at `http://localhost:NNNN/v1` with any +placeholder key. The user never copies their Portal key around — the proxy +rides on the credential Hermes already holds. + +Where this could live in Hermes: + +- `gateway/platforms/api_server.py` is the precedent — it exposes the agent + over a local OpenAI-compatible endpoint, but routes through the full agent + loop (tool calls and all). The proxy variant is **pure inference + pass-through**: no agent loop, no tools, just forward `/chat/completions` + upstream with the user's stored Portal bearer. +- ~150 lines as a new gateway adapter or a plugin under `plugins/`. +- Token refresh: if the browser-OAuth flow produces a refreshable token, the + credential pool's refresh logic already exists. If it's a long-lived static + bearer, even simpler. + +This is genuinely useful and worth shipping — it's the answer to "use my +Portal sub with $external_app without copy-pasting keys." + +--- + +## Real OAuth provider on Portal — when is it worth pitching? + +Only when the consumer is *another first-party Nous thing* (a future SDK, a +Nous-branded extension, a Discord-bot integration that needs per-user +delegation, etc.). Pitching it as the answer to "use my Portal sub with +Karakeep" is selling the user a thing that won't reach them: even if Portal +shipped OAuth tomorrow, Karakeep's LLM-provider config UI is `base_url + +bearer_token` with no OAuth client, no callback handler, no token refresh. +The OpenAI ecosystem standardized on static bearers and downstream apps +won't rebuild their config UX to accommodate a new auth flow. + +The features that would actually help users today, and that Portal could ship +without depending on third-party app changes: + +- **Scoped, named, revocable API keys** with last-used timestamps. Same UX + benefits people want from OAuth (revoke a compromised key, see what's using + the sub, scope a key to specific models), in a shape every existing app + already supports. +- **Per-key rate limits** so a noisy app can be capped without eating the + user's headroom for Hermes itself. + +--- + +## Talking-points cheatsheet (for next time) + +When the user asks "can $APP use my Portal subscription": + +1. First decide: Hermes plugin (runs inside Hermes) or separate app? If plugin, + it already uses Portal via Hermes's provider config — done. +2. If separate app: today, paste the static API key from Portal → API Keys. + Base URL `https://inference-api.nousresearch.com/v1`. Rate limits are + subscription-tier based, applied per-key. +3. If the user pushes back with "but I don't want to paste a key" — that's + the local-broker-proxy answer (Layer 3). Worth building. Not a Portal-side + OAuth roadmap problem. +4. Mixed setup ("Portal for some things, OpenRouter/Ollama Cloud for the + Hermes agent itself") is fully supported. Hermes treats agent + provider/model and tool-side LLM calls as independent config; you can + point each at a different endpoint. + +**Note on the Tool Gateway**: the "no separate accounts, no API key juggling" +pitch in the Tool Gateway announcement is specifically about Hermes Agent's +*tools* (web search, browser, image gen, TTS) flowing through the Portal +subscription when Hermes is configured to use Portal as its provider. It is +**not** a claim that arbitrary third-party apps inherit Portal auth. diff --git a/skills/autonomous-ai-agents/hermes-agent/references/project-context-files.md b/skills/autonomous-ai-agents/hermes-agent/references/project-context-files.md new file mode 100644 index 000000000000..7a6d8ee19071 --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/project-context-files.md @@ -0,0 +1,48 @@ +# Project Context Files + +Hermes injects project-level instructions into the system prompt by reading context files from the working directory. The discovery order is **first match wins** — only one project context source is loaded per session. + +| File (in priority order) | Discovery | Use when | +|---|---|---| +| `.hermes.md` / `HERMES.md` | Walks parents up to the git root, stops at git root | You want hierarchical project rules (root + per-package overrides) | +| `AGENTS.md` / `agents.md` | **Cwd only** — subdirectory and parent copies are ignored | You want portable agent instructions that work the same in Hermes, Claude Code, Codex, etc. | +| `CLAUDE.md` / `claude.md` | Cwd only | Same as AGENTS.md, Claude-flavored | +| `.cursorrules` / `.cursor/rules/*.mdc` | Cwd only | Migrating from Cursor | + +`SOUL.md` (in `$HERMES_HOME`) is independent and always loaded when present — it sets the agent's identity, not project rules. + +### Pick the right one + +- **Use `.hermes.md`** when you want Hermes-specific behavior that lives above the cwd (root + subtree), or when you want rules to inherit from a parent directory. The parent walk stops at the git root, so a home-level `.hermes.md` won't leak into every project (a git repo's root is the boundary). +- **Use `AGENTS.md`** when the same project will also be worked on by other agents (Codex, Claude Code, OpenCode). Those tools all have their own conventions for `AGENTS.md`, and the "cwd only" contract keeps the file portable. +- **Don't put project rules in `~/.hermes/AGENTS.md`** (or any other home-level location). When Hermes runs with that directory as cwd, the file loads — but only for that one directory. For cross-project context, use `SOUL.md` (in `$HERMES_HOME`, identity-only) or install a skill via `hermes skills install`. + +### Size and truncation + +Each context file is capped at 20,000 characters. Files longer than that get **head + tail** truncated (the middle is dropped, with a `[...truncated...]` marker). For large project rules, prefer splitting into multiple skills over cramming one file. + +### Security + +All context files pass through the threat-pattern scanner before reaching the system prompt. Patterns matching prompt injection or promptware are replaced with a `[BLOCKED: ...]` placeholder. This means an `AGENTS.md` containing obvious injection attempts won't reach the model — the scanner blocks the content, not the file, so the rest of the file still loads. + +### Disable for one session + +`hermes --ignore-rules` skips auto-injection of all project context files (`.hermes.md`, `AGENTS.md`, `CLAUDE.md`, `.cursorrules`) **and** `SOUL.md` identity, plus user config, plugins, and MCP servers. Use it to isolate whether a problem is your setup or Hermes itself. + +### Example: a small `.hermes.md` + +```markdown +# My Project + +Hermes: when working in this repo, follow these rules. + +## Build +- Always run `make test` before declaring a change done. +- Use `uv run` for Python, not `pip install`. + +## Style +- Prefer `pathlib.Path` over `os.path`. +- No `print()` in production code — use the `logger`. +``` + +That file at `/home/me/projects/myrepo/.hermes.md` is auto-loaded when Hermes runs in any subdirectory of `/home/me/projects/myrepo`, but not when it runs in `/home/me/other-project`. diff --git a/skills/autonomous-ai-agents/hermes-agent/references/providers-and-models.md b/skills/autonomous-ai-agents/hermes-agent/references/providers-and-models.md new file mode 100644 index 000000000000..5e94a9bf7fc6 --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/providers-and-models.md @@ -0,0 +1,29 @@ +# Providers + +20+ providers supported. Set via `hermes model` or `hermes setup`. + +| Provider | Auth | Key env var | +|----------|------|-------------| +| OpenRouter | API key | `OPENROUTER_API_KEY` | +| Anthropic | API key | `ANTHROPIC_API_KEY` | +| Nous Portal | OAuth | `hermes auth` | +| OpenAI Codex | OAuth | `hermes auth` | +| GitHub Copilot | Token | `COPILOT_GITHUB_TOKEN` | +| Google Gemini | API key | `GOOGLE_API_KEY` or `GEMINI_API_KEY` | +| DeepSeek | API key | `DEEPSEEK_API_KEY` | +| xAI / Grok | API key | `XAI_API_KEY` | +| Hugging Face | Token | `HF_TOKEN` | +| Z.AI / GLM | API key | `GLM_API_KEY` | +| MiniMax | API key | `MINIMAX_API_KEY` | +| MiniMax CN | API key | `MINIMAX_CN_API_KEY` | +| Kimi / Moonshot | API key | `KIMI_API_KEY` | +| Alibaba / DashScope | API key | `DASHSCOPE_API_KEY` | +| Xiaomi MiMo | API key | `XIAOMI_API_KEY` | +| Kilo Code | API key | `KILOCODE_API_KEY` | +| OpenCode Zen | API key | `OPENCODE_ZEN_API_KEY` | +| OpenCode Go | API key | `OPENCODE_GO_API_KEY` | +| Qwen OAuth | OAuth | `hermes auth add qwen-oauth` | +| Custom endpoint | Config | `model.base_url` + `model.api_key` in config.yaml | +| GitHub Copilot ACP | External | `COPILOT_CLI_PATH` or Copilot CLI | + +Full provider docs: https://hermes-agent.nousresearch.com/docs/integrations/providers diff --git a/skills/autonomous-ai-agents/hermes-agent/references/security-privacy.md b/skills/autonomous-ai-agents/hermes-agent/references/security-privacy.md new file mode 100644 index 000000000000..5e7650ccc5f8 --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/security-privacy.md @@ -0,0 +1,55 @@ +# Security & Privacy Toggles + +Common "why is Hermes doing X to my output / tool calls / commands?" toggles — and the exact commands to change them. Most of these need a fresh session (`/reset` in chat, or start a new `hermes` invocation) because they're read once at startup. + +### Secret redaction in tool output + +Secret redaction is **on by default** — tool output (terminal stdout, `read_file`, web content, subagent summaries, etc.) is scanned for strings that look like API keys, tokens, and secrets before it enters the conversation context and logs. Leave it enabled for normal use: + +```bash +hermes config set security.redact_secrets true # keep enabled globally +``` + +**Restart required.** `security.redact_secrets` is snapshotted at import time — toggling it mid-session (e.g. via `export HERMES_REDACT_SECRETS=false` from a tool call) will NOT take effect for the running process. Tell the user to change it in config from a terminal, then start a new session. This is deliberate — it prevents an LLM from flipping the toggle on itself mid-task. + +Disable only when you deliberately need raw credential-like strings for debugging or redactor development: +```bash +hermes config set security.redact_secrets false +``` + +### PII redaction in gateway messages + +Separate from secret redaction. When enabled, the gateway hashes user IDs and strips phone numbers from the session context before it reaches the model: + +```bash +hermes config set privacy.redact_pii true # enable +hermes config set privacy.redact_pii false # disable (default) +``` + +### Command approval prompts + +By default (`approvals.mode: smart`), Hermes asks an auxiliary LLM to assess shell commands flagged as destructive (`rm -rf`, `git reset --hard`, etc.). The modes are: + +- `smart` — auto-approve a low-risk command once, deny high-risk commands, and prompt when uncertain (default) +- `manual` — always prompt +- `off` — skip all approval prompts (equivalent to `--yolo`) + +```bash +hermes config set approvals.mode smart # recommended middle ground +hermes config set approvals.mode off # bypass everything (not recommended) +``` + +Per-invocation bypass without changing config: +- `hermes --yolo …` +- `export HERMES_YOLO_MODE=1` + +Note: YOLO / `approvals.mode: off` does NOT turn off secret redaction. They are independent. + +### Shell hooks allowlist + +Some shell-hook integrations require explicit allowlisting before they fire. Managed via `~/.hermes/shell-hooks-allowlist.json` — prompted interactively the first time a hook wants to run. + +### Disabling the web/browser/image-gen tools + +To keep the model away from network or media tools entirely, open `hermes tools` and toggle per-platform. Takes effect on next session (`/reset`). See the Tools & Skills section above. + diff --git a/skills/autonomous-ai-agents/hermes-agent/references/slash-commands.md b/skills/autonomous-ai-agents/hermes-agent/references/slash-commands.md new file mode 100644 index 000000000000..f6813f75f639 --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/slash-commands.md @@ -0,0 +1,101 @@ +# Slash Commands (In-Session) + +Type these during an interactive chat session. New commands land fairly +often; if something below looks stale, run `/help` in-session for the +authoritative list or see the [live slash commands reference](https://hermes-agent.nousresearch.com/docs/reference/slash-commands). +The registry of record is `hermes_cli/commands.py` — every consumer +(autocomplete, Telegram menu, Slack mapping, `/help`) derives from it. + +### Session Control +``` +/new (/reset) Fresh session +/clear Clear screen + new session (CLI) +/retry Resend last message +/undo Remove last exchange +/title [name] Name the session +/compress Manually compress context +/stop Kill background processes +/rollback [N] Restore filesystem checkpoint +/snapshot [sub] Create or restore state snapshots of Hermes config/state (CLI) +/background Run prompt in background +/queue Queue for next turn +/steer Inject a message after the next tool call without interrupting +/agents (/tasks) Show active agents and running tasks +/resume [name] Resume a named session +/goal [text|sub] Set a standing goal Hermes works on across turns until achieved + (subcommands: status, pause, resume, clear) +/redraw Force a full UI repaint (CLI) +``` + +### Configuration +``` +/config Show config (CLI) +/model [name] Show or change model +/personality [name] Set personality +/reasoning [level] Set reasoning (none|minimal|low|medium|high|xhigh|max|ultra|show|hide) +/verbose Cycle: off → new → all → verbose +/voice [on|off|tts] Voice mode +/yolo Toggle approval bypass +/busy [sub] Control what Enter does while Hermes is working (CLI) + (subcommands: queue, steer, interrupt, status) +/indicator [style] Pick the TUI busy-indicator style (CLI) + (styles: kaomoji, emoji, unicode, ascii) +/footer [on|off] Toggle gateway runtime-metadata footer on final replies +/skin [name] Change theme (CLI) +/statusbar Toggle status bar (CLI) +``` + +### Tools & Skills +``` +/tools Manage tools (CLI) +/toolsets List toolsets (CLI) +/skills Search/install skills (CLI) +/skill Load a skill into session +/reload-skills Re-scan ~/.hermes/skills/ for added/removed skills +/reload Reload .env variables into the running session (CLI) +/reload-mcp Reload MCP servers +/cron Manage cron jobs (CLI) +/curator [sub] Background skill maintenance (status, run, pin, archive, …) +/kanban [sub] Multi-profile collaboration board (tasks, links, comments) +/plugins List plugins (CLI) +``` + +### Gateway +``` +/approve Approve a pending command (gateway) +/deny Deny a pending command (gateway) +/restart Restart gateway (gateway) +/sethome Set current chat as home channel (gateway) +/update Update Hermes to latest (gateway) +/topic [sub] Enable or inspect Telegram DM topic sessions (gateway) +/platforms (/gateway) Show platform connection status (gateway) +``` + +### Utility +``` +/branch (/fork) Branch the current session +/handoff Hand the live session off to a messaging platform (CLI) +/fast Toggle priority/fast processing +/browser Open CDP browser connection +/history Show conversation history (CLI) +/save Save conversation to file (CLI) +/copy [N] Copy the last assistant response to clipboard (CLI) +/paste Attach clipboard image (CLI) +/image Attach local image file (CLI) +``` + +### Info +``` +/help Show commands +/commands [page] Browse all commands (gateway) +/usage Token usage +/insights [days] Usage analytics +/status Session info (gateway) +/profile Active profile info +/debug Upload debug report (system info + logs) and get shareable links +``` + +### Exit +``` +/quit (/exit, /q) Exit CLI +``` diff --git a/skills/hermes-themes/SKILL.md b/skills/autonomous-ai-agents/hermes-agent/references/themes.md similarity index 96% rename from skills/hermes-themes/SKILL.md rename to skills/autonomous-ai-agents/hermes-agent/references/themes.md index 15982af0c8f4..b4ded40cb0ca 100644 --- a/skills/hermes-themes/SKILL.md +++ b/skills/autonomous-ai-agents/hermes-agent/references/themes.md @@ -1,15 +1,4 @@ ---- -name: hermes-themes -description: "Author a Hermes color theme that skins every surface." -version: 1.0.0 -platforms: [linux, macos, windows] -metadata: - hermes: - tags: [theme, skin, appearance, cli, tui, desktop, self-config] - related_skills: [] ---- - -# Hermes Themes Skill +# Themes / Skins — Author a Hermes Color Theme Author a Hermes **skin** — one YAML file that themes the CLI, the TUI, and the desktop GUI at once. The skin engine (`hermes_cli/skin_engine.py`) resolves the diff --git a/skills/autonomous-ai-agents/hermes-agent/references/troubleshooting.md b/skills/autonomous-ai-agents/hermes-agent/references/troubleshooting.md new file mode 100644 index 000000000000..75bbccb7aebc --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/troubleshooting.md @@ -0,0 +1,51 @@ +# Troubleshooting + +### Voice not working +1. Check `stt.enabled: true` in config.yaml +2. Verify provider: `pip install faster-whisper` or set API key +3. In gateway: `/restart`. In CLI: exit and relaunch. + +### Tool not available +1. `hermes tools` — check if toolset is enabled for your platform +2. Some tools need env vars (check `.env`) +3. `/reset` after enabling tools + +### Model/provider issues +1. `hermes doctor` — check config and dependencies +2. `hermes auth` — re-authenticate OAuth providers (or `hermes auth add `) +3. Check `.env` has the right API key +4. **Copilot 403**: `gh auth login` tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via `hermes model` → GitHub Copilot. + +### Changes not taking effect +- **Tools/skills:** `/reset` starts a new session with updated toolset +- **Config changes:** In gateway: `/restart`. In CLI: exit and relaunch. +- **Code changes:** Restart the CLI or gateway process + +### Skills not showing +1. `hermes skills list` — verify installed +2. `hermes skills config` — check platform enablement +3. Load explicitly: `/skill name` or `hermes -s name` + +### Gateway issues +Check logs first: +```bash +grep -i "failed to send\|error" ~/.hermes/logs/gateway.log | tail -20 +``` + +Common gateway problems: +- **Gateway dies on SSH logout**: Enable linger: `sudo loginctl enable-linger $USER` +- **Gateway dies on WSL2 close**: WSL2 requires `systemd=true` in `/etc/wsl.conf` for systemd services to work. Without it, gateway falls back to `nohup` (dies when session closes). +- **Gateway crash loop**: Reset the failed state: `systemctl --user reset-failed hermes-gateway` + +### Platform-specific issues +- **Discord bot silent**: Must enable **Message Content Intent** in Bot → Privileged Gateway Intents. +- **Slack bot only works in DMs**: Must subscribe to `message.channels` event. Without it, the bot ignores public channels. +- **Windows-specific issues** (`Alt+Enter` newline, WinError 10106, UTF-8 BOM config, test suite, line endings): see the dedicated **Windows-Specific Quirks** section above. + +### Auxiliary models not working +If `auxiliary` tasks (vision, compression, session_search) fail silently, the `auto` provider can't find a backend. Either set `OPENROUTER_API_KEY` or `GOOGLE_API_KEY`, or explicitly configure each auxiliary task's provider: +```bash +hermes config set auxiliary.vision.provider +hermes config set auxiliary.vision.model +``` + diff --git a/skills/productivity/tui-widgets/SKILL.md b/skills/autonomous-ai-agents/hermes-agent/references/tui-widgets.md similarity index 96% rename from skills/productivity/tui-widgets/SKILL.md rename to skills/autonomous-ai-agents/hermes-agent/references/tui-widgets.md index 796f12a370e6..c9eb6717f05e 100644 --- a/skills/productivity/tui-widgets/SKILL.md +++ b/skills/autonomous-ai-agents/hermes-agent/references/tui-widgets.md @@ -1,16 +1,4 @@ ---- -name: tui-widgets -description: Author live widget apps for the Hermes TUI dock. -version: 1.0.0 -author: Hermes Agent -license: MIT -metadata: - hermes: - tags: [tui, widgets, sdk, ui] - category: productivity ---- - -# TUI Widgets Skill +# TUI Widgets — Live Panels for the Ink TUI Dock Author widget apps for the Hermes TUI (`hermes --tui`): glanceable ambient panels docked above the status bar, or modal overlays that own the keyboard. diff --git a/skills/autonomous-ai-agents/hermes-agent/references/windows-quirks.md b/skills/autonomous-ai-agents/hermes-agent/references/windows-quirks.md new file mode 100644 index 000000000000..bf2eee616c57 --- /dev/null +++ b/skills/autonomous-ai-agents/hermes-agent/references/windows-quirks.md @@ -0,0 +1,57 @@ +# Windows-Specific Quirks + +Hermes runs natively on Windows (PowerShell, cmd, Windows Terminal, git-bash +mintty, VS Code integrated terminal). Most of it just works, but a handful +of differences between Win32 and POSIX have bitten us — document new ones +here as you hit them so the next person (or the next session) doesn't +rediscover them from scratch. + +### Input / Keybindings + +**Alt+Enter doesn't insert a newline** — Windows Terminal (and mintty) grab it +for fullscreen before prompt_toolkit sees it. Use **Ctrl+Enter** instead (the +CLI binds it to newline on Windows; raw Ctrl+J does the same, harmlessly). +To inspect how your terminal reports a keystroke, run +`python scripts/keystroke_diagnostic.py` from the repo root. + +### Config / Files + +**HTTP 400 "No models provided" on first run** — `config.yaml` was saved with +a UTF-8 BOM (Notepad does this). Re-save as UTF-8 without BOM; +`hermes config edit` writes correctly. + +### `execute_code` / Sandbox + +**WinError 10106** from the sandbox child process — it can't create an +`AF_INET` socket. Root cause is usually Hermes's env scrubber dropping +`SYSTEMROOT`/`WINDIR`/`COMSPEC` (Python's `socket` needs `SYSTEMROOT` to find +`mswsock.dll`), not a broken Winsock LSP. The `_WINDOWS_ESSENTIAL_ENV_VARS` +allowlist in `tools/code_execution_tool.py` covers it; if you still hit it, +echo `os.environ` inside an `execute_code` block to confirm `SYSTEMROOT` is set. + +### Testing on Windows + +`scripts/run_tests.sh` is POSIX-only (expects `.venv/bin/activate`); the +Hermes-installed `venv/Scripts/` has no pip/pytest (stripped for size). +Install pytest into a system Python and run directly with `-n 0` +(`pyproject.toml`'s `addopts` already sets `-n`): + +```bash +"/c/Program Files/Python311/python" -m pip install --user pytest pytest-xdist pyyaml +export PYTHONPATH="$(pwd)" +"/c/Program Files/Python311/python" -m pytest tests/foo/test_bar.py -v --tb=short -n 0 +``` + +(POSIX-only tests need skip guards — see the cross-platform guard list in the +Contributor section below.) + +### Path / Filesystem + +**Line endings.** Git may warn `LF will be replaced by CRLF`. Cosmetic — the +repo's `.gitattributes` normalizes. Don't let editors auto-convert committed +POSIX-newline files to CRLF. + +**Forward slashes work almost everywhere.** `C:/Users/...` is accepted by +every Hermes tool and most Windows APIs. Prefer forward slashes in code +and logs — avoids shell-escaping backslashes in bash. + diff --git a/skills/productivity/tui-widgets/templates/clock.mjs b/skills/autonomous-ai-agents/hermes-agent/templates/clock.mjs similarity index 100% rename from skills/productivity/tui-widgets/templates/clock.mjs rename to skills/autonomous-ai-agents/hermes-agent/templates/clock.mjs diff --git a/skills/hermes-desktop-plugins/templates/plugin.js b/skills/autonomous-ai-agents/hermes-agent/templates/plugin.js similarity index 100% rename from skills/hermes-desktop-plugins/templates/plugin.js rename to skills/autonomous-ai-agents/hermes-agent/templates/plugin.js diff --git a/skills/hermes-themes/templates/skin.yaml b/skills/autonomous-ai-agents/hermes-agent/templates/skin.yaml similarity index 100% rename from skills/hermes-themes/templates/skin.yaml rename to skills/autonomous-ai-agents/hermes-agent/templates/skin.yaml diff --git a/website/docs/reference/skills-catalog.md b/website/docs/reference/skills-catalog.md index f340bdd3305f..a5eff43a69b4 100644 --- a/website/docs/reference/skills-catalog.md +++ b/website/docs/reference/skills-catalog.md @@ -27,7 +27,7 @@ If a skill is missing from this list but present in the repo, the catalog is reg |-------|-------------|------| | [`claude-code`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-claude-code) | Delegate coding to Claude Code CLI (features, PRs). | `autonomous-ai-agents/claude-code` | | [`codex`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-codex) | Delegate coding to OpenAI Codex CLI (features, PRs). | `autonomous-ai-agents/codex` | -| [`hermes-agent`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent) | Configure, extend, or contribute to Hermes Agent. | `autonomous-ai-agents/hermes-agent` | +| [`hermes-agent`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent) | Use, configure, theme, extend, and orchestrate Hermes Agent. | `autonomous-ai-agents/hermes-agent` | | [`opencode`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-opencode) | Delegate coding to OpenCode CLI (features, PR review). | `autonomous-ai-agents/opencode` | ## computer-use @@ -74,12 +74,6 @@ If a skill is missing from this list but present in the repo, the catalog is reg | [`github-pr-workflow`](/docs/user-guide/skills/bundled/github/github-github-pr-workflow) | GitHub PR lifecycle: branch, commit, open, CI, merge. | `github/github-pr-workflow` | | [`github-repo-management`](/docs/user-guide/skills/bundled/github/github-github-repo-management) | Clone/create/fork repos; manage remotes, releases. | `github/github-repo-management` | -## hermes-desktop-plugins - -| Skill | Description | Path | -|-------|-------------|------| -| [`hermes-desktop-plugins`](/docs/user-guide/skills/bundled/hermes-desktop-plugins/hermes-desktop-plugins-hermes-desktop-plugins) | Write desktop app plugins that add UI panes and commands. | `hermes-desktop-plugins` | - ## media | Skill | Description | Path | @@ -119,7 +113,6 @@ If a skill is missing from this list but present in the repo, the catalog is reg | [`notion`](/docs/user-guide/skills/bundled/productivity/productivity-notion) | Notion API + ntn CLI: pages, databases, markdown, Workers. | `productivity/notion` | | [`ocr-and-documents`](/docs/user-guide/skills/bundled/productivity/productivity-ocr-and-documents) | Extract text from PDFs/scans (pymupdf, marker-pdf). | `productivity/ocr-and-documents` | | [`pdf`](/docs/user-guide/skills/bundled/productivity/productivity-pdf) | Create, merge, split, fill, and secure PDF files. | `productivity/pdf` | -| [`petdex`](/docs/user-guide/skills/bundled/productivity/productivity-petdex) | Install and select animated petdex mascots for Hermes. | `productivity/petdex` | | [`powerpoint`](/docs/user-guide/skills/bundled/productivity/productivity-powerpoint) | Create, read, edit .pptx decks, slides, notes, templates. | `productivity/powerpoint` | | [`teams-meeting-pipeline`](/docs/user-guide/skills/bundled/productivity/productivity-teams-meeting-pipeline) | Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions. | `productivity/teams-meeting-pipeline` | | [`xlsx`](/docs/user-guide/skills/bundled/productivity/productivity-xlsx) | Create, read, edit Excel .xlsx spreadsheets and CSVs. | `productivity/xlsx` | diff --git a/website/docs/user-guide/features/pets.md b/website/docs/user-guide/features/pets.md index e2b0bbe65d56..de082f36c8a1 100644 --- a/website/docs/user-guide/features/pets.md +++ b/website/docs/user-guide/features/pets.md @@ -206,5 +206,6 @@ Common gotchas: ## See also -- The [`petdex` skill](../skills/bundled/productivity/productivity-petdex.md) - lets the agent install and switch pets for you on request. +- The [`hermes-agent` skill](../skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent.md) + lets the agent install and switch pets for you on request (see its + `references/petdex.md`). diff --git a/website/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent.md b/website/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent.md index 2dde2ad9d124..432ce68b46ff 100644 --- a/website/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent.md +++ b/website/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent.md @@ -1,14 +1,14 @@ --- -title: "Hermes Agent — Configure, extend, or contribute to Hermes Agent" +title: "Hermes Agent — Use, configure, theme, extend, and orchestrate Hermes Agent" sidebar_label: "Hermes Agent" -description: "Configure, extend, or contribute to Hermes Agent" +description: "Use, configure, theme, extend, and orchestrate Hermes Agent" --- {/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */} # Hermes Agent -Configure, extend, or contribute to Hermes Agent. +Use, configure, theme, extend, and orchestrate Hermes Agent. ## Skill metadata @@ -16,11 +16,11 @@ Configure, extend, or contribute to Hermes Agent. |---|---| | Source | Bundled (installed by default) | | Path | `skills/autonomous-ai-agents/hermes-agent` | -| Version | `2.1.0` | +| Version | `3.0.0` | | Author | Hermes Agent + Teknium | | License | MIT | | Platforms | linux, macos, windows | -| Tags | `hermes`, `setup`, `configuration`, `multi-agent`, `spawning`, `cli`, `gateway`, `development` | +| Tags | `hermes`, `setup`, `configuration`, `multi-agent`, `spawning`, `cli`, `gateway`, `themes`, `skins`, `desktop-plugins`, `tui-widgets`, `petdex`, `development` | | Related skills | [`claude-code`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-claude-code), [`codex`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-codex), [`opencode`](/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-opencode) | ## Reference: full SKILL.md @@ -31,529 +31,98 @@ The following is the complete skill definition that Hermes loads when this skill # Hermes Agent -Hermes Agent is an open-source AI agent framework by Nous Research that runs in your terminal, messaging platforms, and IDEs. It belongs to the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Hermes works with any LLM provider (OpenRouter, Anthropic, OpenAI, DeepSeek, local models, and 15+ others) and runs on Linux, macOS, and WSL. +Hermes Agent is an open-source AI agent framework by Nous Research that runs in your terminal, a native desktop app, messaging platforms, and IDEs. It's in the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Hermes works with any LLM provider (OpenRouter, Anthropic, OpenAI, Google, DeepSeek, xAI, local models, and 20+ others) and runs on Linux, macOS, Windows, and WSL. What makes Hermes different: -- **Self-improving through skills** — Hermes learns from experience by saving reusable procedures as skills. When it solves a complex problem, discovers a workflow, or gets corrected, it can persist that knowledge as a skill document that loads into future sessions. Skills accumulate over time, making the agent better at your specific tasks and environment. -- **Persistent memory across sessions** — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends (built-in, Honcho, Mem0, and more) let you choose how memory works. -- **Multi-platform gateway** — the same agent runs on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 10+ other platforms with full tool access, not just chat. -- **Provider-agnostic** — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically. +- **Self-improving through skills** — Hermes learns from experience by saving reusable procedures as skills that load into future sessions. +- **Persistent memory across sessions** — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends. +- **Multi-platform gateway** — the same agent runs on Telegram, Discord, Slack, WhatsApp, iMessage, Signal, Matrix, Teams, Email, and a dozen more platforms with full tool access, not just chat. +- **Many surfaces** — the same agent core drives the CLI, the Ink TUI, a native Electron desktop app, a web dashboard, and an ACP server for IDEs (VS Code / Zed / JetBrains). +- **Provider-agnostic** — swap models and providers mid-workflow; credential pools rotate across multiple API keys automatically. - **Profiles** — run multiple independent Hermes instances with isolated configs, sessions, skills, and memory. -- **Extensible** — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem. +- **Extensible & themeable** — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, skins that theme every surface, desktop UI plugins, TUI widgets, and pet mascots. -People use Hermes for software development, research, system administration, data analysis, content creation, home automation, and anything else that benefits from an AI agent with persistent context and full system access. - -**This skill helps you work with Hermes Agent effectively** — setting it up, configuring features, spawning additional agent instances, troubleshooting issues, finding the right commands and settings, and understanding how the system works when you need to extend or contribute to it. +**This skill is a hub.** The body covers identity, quick start, spawning/orchestration, and hard invariants. Everything else lives in reference files — **load the matching reference (below) before answering**; do not answer detail questions from the body alone. **Docs:** https://hermes-agent.nousresearch.com/docs/ +## Scope & Verification + +This skill is a concise operating guide, not the complete source of truth for every Hermes feature. If a Hermes feature, command, or setting is not mentioned here or in a reference, do not treat that absence as evidence that it does not exist. Check the live repository and official docs before giving a negative answer. + +Good verification targets: + +- CLI commands: `hermes --help`, `hermes --help`, and `hermes_cli/main.py` +- User documentation: https://hermes-agent.nousresearch.com/docs/ +- Source tree: https://github.com/NousResearch/hermes-agent + ## Quick Start ```bash -# Install +# Install (shell installer — sets up uv, Python, the venv, and the launcher) curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash -# Interactive chat (default) +# Interactive chat (default surface; set display.interface: tui to launch the Ink TUI instead) hermes # Single query hermes chat -q "What is the capital of France?" -# Setup wizard +# Setup wizard / pick model+provider / health check hermes setup - -# Change model/provider hermes model - -# Check health hermes doctor + +# Other surfaces +hermes desktop # launch the native desktop app (alias: hermes gui) +hermes dashboard # web admin panel + embedded chat +hermes proxy # OpenAI-compatible local proxy backed by your OAuth provider ``` ---- - -## CLI Reference - -### Global Flags +## Key Paths ``` -hermes [flags] [command] - - --version, -V Show version - --resume, -r SESSION Resume session by ID or title - --continue, -c [NAME] Resume by name, or most recent session - --worktree, -w Isolated git worktree mode (parallel agents) - --skills, -s SKILL Preload skills (comma-separate or repeat) - --profile, -p NAME Use a named profile - --yolo Skip dangerous command approval - --pass-session-id Include session ID in system prompt -``` - -No subcommand defaults to `chat`. - -### Chat - -``` -hermes chat [flags] - -q, --query TEXT Single query, non-interactive - -m, --model MODEL Model (e.g. anthropic/claude-sonnet-4) - -t, --toolsets LIST Comma-separated toolsets - --provider PROVIDER Force provider (openrouter, anthropic, nous, etc.) - -v, --verbose Verbose output - -Q, --quiet Suppress banner, spinner, tool previews - --checkpoints Enable filesystem checkpoints (/rollback) - --source TAG Session source tag (default: cli) -``` - -### Configuration - -``` -hermes setup [section] Interactive wizard (model|terminal|gateway|tools|agent) -hermes model Interactive model/provider picker -hermes config View current config -hermes config edit Open config.yaml in $EDITOR -hermes config set KEY VAL Set a config value -hermes config path Print config.yaml path -hermes config env-path Print .env path -hermes config check Check for missing/outdated config -hermes config migrate Update config with new options -hermes auth Interactive credential manager -hermes auth add PROVIDER Add OAuth or API-key credential (e.g. nous, openai-codex, qwen-oauth) -hermes auth list List stored credentials -hermes auth remove PROVIDER Remove a stored credential -hermes doctor [--fix] Check dependencies and config -hermes status [--all] Show component status -``` - -### Tools & Skills - -``` -hermes tools Interactive tool enable/disable (curses UI) -hermes tools list Show all tools and status -hermes tools enable NAME Enable a toolset -hermes tools disable NAME Disable a toolset - -hermes skills list List installed skills -hermes skills search QUERY Search the skills hub -hermes skills install ID Install a skill (ID can be a hub identifier OR a direct https://…/SKILL.md URL; pass --name to override when frontmatter has no name) -hermes skills inspect ID Preview without installing -hermes skills config Enable/disable skills per platform -hermes skills check Check for updates -hermes skills update Update outdated skills -hermes skills uninstall N Remove a hub skill -hermes skills publish PATH Publish to registry -hermes skills browse Browse all available skills -hermes skills tap add REPO Add a GitHub repo as skill source -``` - -### MCP Servers - -``` -hermes mcp serve Run Hermes as an MCP server -hermes mcp add NAME Add an MCP server (--url or --command) -hermes mcp remove NAME Remove an MCP server -hermes mcp list List configured servers -hermes mcp test NAME Test connection -hermes mcp configure NAME Toggle tool selection -``` - -How the built-in MCP client connects servers (stdio/HTTP), auto-discovers -their tools, and exposes them as first-class tools, plus catalog install -(`hermes mcp install `): `skill_view(name="hermes-agent", file_path="references/native-mcp.md")`. - -### Gateway (Messaging Platforms) - -``` -hermes gateway run Start gateway foreground -hermes gateway install Install as background service -hermes gateway start/stop Control the service -hermes gateway restart Restart the service -hermes gateway status Check status -hermes gateway setup Configure platforms -``` - -Supported platforms: Telegram, Discord, Slack, WhatsApp, Signal, Email, SMS, Matrix, Mattermost, Home Assistant, DingTalk, Feishu, WeCom, BlueBubbles (iMessage), Weixin (WeChat), API Server, Webhooks. Open WebUI connects via the API Server adapter. - -Platform docs: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/ - -### Sessions - -``` -hermes sessions list List recent sessions -hermes sessions browse Interactive picker -hermes sessions export OUT Export to JSONL -hermes sessions rename ID T Rename a session -hermes sessions delete ID Delete a session -hermes sessions prune Clean up old sessions (--older-than N days) -hermes sessions stats Session store statistics -``` - -### Cron Jobs - -``` -hermes cron list List jobs (--all for disabled) -hermes cron create SCHED Create: '30m', 'every 2h', '0 9 * * *' -hermes cron edit ID Edit schedule, prompt, delivery -hermes cron pause/resume ID Control job state -hermes cron run ID Trigger on next tick -hermes cron remove ID Delete a job -hermes cron status Scheduler status -``` - -### Webhooks - -``` -hermes webhook subscribe N Create route at /webhooks/ -hermes webhook list List subscriptions -hermes webhook remove NAME Remove a subscription -hermes webhook test NAME Send a test POST -``` - -Full setup, route config, payload templating, and event-driven agent-run -patterns: `skill_view(name="hermes-agent", file_path="references/webhooks.md")`. - -### Profiles - -``` -hermes profile list List all profiles -hermes profile create NAME Create (--clone, --clone-all, --clone-from) -hermes profile use NAME Set sticky default -hermes profile delete NAME Delete a profile -hermes profile show NAME Show details -hermes profile alias NAME Manage wrapper scripts -hermes profile rename A B Rename a profile -hermes profile export NAME Export to tar.gz -hermes profile import FILE Import from archive -``` - -### Credential Pools - -``` -hermes auth add Interactive credential wizard -hermes auth list [PROVIDER] List pooled credentials -hermes auth remove P INDEX Remove by provider + index -hermes auth reset PROVIDER Clear exhaustion status -``` - -### Other - -``` -hermes insights [--days N] Usage analytics -hermes update Update to latest version -hermes pairing list/approve/revoke DM authorization -hermes plugins list/install/remove Plugin management -hermes honcho setup/status Honcho memory integration (requires honcho plugin) -hermes memory setup/status/off Memory provider config -hermes completion bash|zsh Shell completions -hermes acp ACP server (IDE integration) -hermes claw migrate Migrate from OpenClaw -hermes uninstall Uninstall Hermes -``` - ---- - -## Slash Commands (In-Session) - -Type these during an interactive chat session. New commands land fairly -often; if something below looks stale, run `/help` in-session for the -authoritative list or see the [live slash commands reference](https://hermes-agent.nousresearch.com/docs/reference/slash-commands). -The registry of record is `hermes_cli/commands.py` — every consumer -(autocomplete, Telegram menu, Slack mapping, `/help`) derives from it. - -### Session Control -``` -/new (/reset) Fresh session -/clear Clear screen + new session (CLI) -/retry Resend last message -/undo Remove last exchange -/title [name] Name the session -/compress Manually compress context -/stop Kill background processes -/rollback [N] Restore filesystem checkpoint -/snapshot [sub] Create or restore state snapshots of Hermes config/state (CLI) -/background Run prompt in background -/queue Queue for next turn -/steer Inject a message after the next tool call without interrupting -/agents (/tasks) Show active agents and running tasks -/resume [name] Resume a named session -/goal [text|sub] Set a standing goal Hermes works on across turns until achieved - (subcommands: status, pause, resume, clear) -/redraw Force a full UI repaint (CLI) -``` - -### Configuration -``` -/config Show config (CLI) -/model [name] Show or change model -/personality [name] Set personality -/reasoning [level] Set reasoning (none|minimal|low|medium|high|xhigh|max|ultra|show|hide) -/verbose Cycle: off → new → all → verbose -/voice [on|off|tts] Voice mode -/yolo Toggle approval bypass -/busy [sub] Control what Enter does while Hermes is working (CLI) - (subcommands: queue, steer, interrupt, status) -/indicator [style] Pick the TUI busy-indicator style (CLI) - (styles: kaomoji, emoji, unicode, ascii) -/footer [on|off] Toggle gateway runtime-metadata footer on final replies -/skin [name] Change theme (CLI) -/statusbar Toggle status bar (CLI) -``` - -### Tools & Skills -``` -/tools Manage tools (CLI) -/toolsets List toolsets (CLI) -/skills Search/install skills (CLI) -/skill Load a skill into session -/reload-skills Re-scan ~/.hermes/skills/ for added/removed skills -/reload Reload .env variables into the running session (CLI) -/reload-mcp Reload MCP servers -/cron Manage cron jobs (CLI) -/curator [sub] Background skill maintenance (status, run, pin, archive, …) -/kanban [sub] Multi-profile collaboration board (tasks, links, comments) -/plugins List plugins (CLI) -``` - -### Gateway -``` -/approve Approve a pending command (gateway) -/deny Deny a pending command (gateway) -/restart Restart gateway (gateway) -/sethome Set current chat as home channel (gateway) -/update Update Hermes to latest (gateway) -/topic [sub] Enable or inspect Telegram DM topic sessions (gateway) -/platforms (/gateway) Show platform connection status (gateway) -``` - -### Utility -``` -/branch (/fork) Branch the current session -/fast Toggle priority/fast processing -/browser Open CDP browser connection -/history Show conversation history (CLI) -/save Save conversation to file (CLI) -/copy [N] Copy the last assistant response to clipboard (CLI) -/paste Attach clipboard image (CLI) -/image Attach local image file (CLI) -``` - -### Info -``` -/help Show commands -/commands [page] Browse all commands (gateway) -/usage Token usage -/insights [days] Usage analytics -/status Session info (gateway) -/profile Active profile info -/debug Upload debug report (system info + logs) and get shareable links -``` - -### Exit -``` -/quit (/exit, /q) Exit CLI -``` - ---- - -## Key Paths & Config - -``` -~/.hermes/config.yaml Main configuration -~/.hermes/.env API keys and secrets (under $HERMES_HOME if set) +~/.hermes/config.yaml Main configuration (settings — never secrets) +~/.hermes/.env API keys and secrets ONLY (under $HERMES_HOME if set) $HERMES_HOME/skills/ Installed skills -~/.hermes/sessions/ Gateway routing index, request dumps, *.jsonl transcripts (and optional per-session JSON snapshots when sessions.write_json_snapshots: true) +~/.hermes/skins/ Custom themes (see references/themes.md) +~/.hermes/desktop-plugins/ Desktop app UI plugins (see references/desktop-plugins.md) +~/.hermes/tui-widgets/ TUI widget apps (see references/tui-widgets.md) +~/.hermes/pets/ Installed pet mascots (see references/petdex.md) ~/.hermes/state.db Canonical session store (SQLite + FTS5) +~/.hermes/sessions/ Gateway routing index, request dumps, *.jsonl transcripts ~/.hermes/logs/ Gateway and error logs ~/.hermes/auth.json OAuth tokens and credential pools ~/.hermes/hermes-agent/ Source code (if git-installed) ``` -Profiles use `~/.hermes/profiles//` with the same layout. +Profiles use `~/.hermes/profiles//` with the same layout. When a profile is active, resolve the real home from `$HERMES_HOME` — never hardcode `~/.hermes`. -### Config Sections +## Routing Table — load the reference for the task -Edit with `hermes config edit` or `hermes config set section.key value`. +| User wants... | Load | +|---|---| +| CLI commands, subcommands, flags, "how do I run X" | `references/cli-reference.md` | +| In-session slash commands | `references/slash-commands.md` | +| Provider setup, API keys, OAuth | `references/providers-and-models.md` | +| config.yaml sections, toolsets, voice/STT/TTS | `references/configuration.md` | +| AGENTS.md / .hermes.md / CLAUDE.md project rules | `references/project-context-files.md` | +| Secret redaction, PII, approval modes, "reset permissions" | `references/security-privacy.md` | +| Delegation, cron, curator, kanban | `references/background-systems.md` | +| MCP servers (add, catalog, `hermes mcp`) | `references/native-mcp.md` | +| Webhook routes and event-driven runs | `references/webhooks.md` | +| A custom theme/skin ("synthwave theme", "change the gold ●") | `references/themes.md` + `templates/skin.yaml` | +| A desktop app UI element (pane, widget, ⌘K command, page) | `references/desktop-plugins.md` + `templates/plugin.js` | +| A live TUI panel or modal widget (ticker, clock, dashboard) | `references/tui-widgets.md` + `templates/clock.mjs` | +| Pet mascots — install, select, scale, diagnose | `references/petdex.md` | +| Windows-specific issues (keybinds, WinError 10106, BOM) | `references/windows-quirks.md` | +| Debugging: voice, tools missing, gateway, aux models | `references/troubleshooting.md` | +| Contributing code: adding tools, slash commands, tests | `references/contributor-guide.md` | +| delegate_task "capped at N" reports | `references/delegate-task-concurrency-diagnosis.md` | +| "Can app X use my Nous Portal subscription/OAuth?" | `references/portal-auth-for-third-party-apps.md` | -| Section | Key options | -|---------|-------------| -| `model` | `default`, `provider`, `base_url`, `api_key`, `context_length` (explicit override; clear to `""` for auto-detect from server `/v1/models`) | -| `agent` | `max_turns` (90), `tool_use_enforcement` | -| `terminal` | `backend` (local/docker/ssh/modal), `cwd`, `timeout` (180) | -| `compression` | `enabled`, `threshold` (0.50), `target_ratio` (0.20) | -| `display` | `skin`, `tool_progress`, `show_reasoning`, `show_cost` | -| `stt` | `enabled`, `provider` (local/groq/openai/mistral) | -| `tts` | `provider` (edge/elevenlabs/openai/minimax/mistral/neutts) | -| `memory` | `memory_enabled`, `user_profile_enabled`, `provider` | -| `security` | `tirith_enabled`, `website_blocklist` | -| `delegation` | `model`, `provider`, `base_url`, `api_key`, `max_iterations` (50), `reasoning_effort` | -| `checkpoints` | `enabled`, `max_snapshots` (50) | - -Full config reference: https://hermes-agent.nousresearch.com/docs/user-guide/configuration - -### Providers - -20+ providers supported. Set via `hermes model` or `hermes setup`. - -| Provider | Auth | Key env var | -|----------|------|-------------| -| OpenRouter | API key | `OPENROUTER_API_KEY` | -| Anthropic | API key | `ANTHROPIC_API_KEY` | -| Nous Portal | OAuth | `hermes auth` | -| OpenAI Codex | OAuth | `hermes auth` | -| GitHub Copilot | Token | `COPILOT_GITHUB_TOKEN` | -| Google Gemini | API key | `GOOGLE_API_KEY` or `GEMINI_API_KEY` | -| DeepSeek | API key | `DEEPSEEK_API_KEY` | -| xAI / Grok | API key | `XAI_API_KEY` | -| Hugging Face | Token | `HF_TOKEN` | -| Z.AI / GLM | API key | `GLM_API_KEY` | -| MiniMax | API key | `MINIMAX_API_KEY` | -| MiniMax CN | API key | `MINIMAX_CN_API_KEY` | -| Kimi / Moonshot | API key | `KIMI_API_KEY` | -| Alibaba / DashScope | API key | `DASHSCOPE_API_KEY` | -| Xiaomi MiMo | API key | `XIAOMI_API_KEY` | -| Kilo Code | API key | `KILOCODE_API_KEY` | -| OpenCode Zen | API key | `OPENCODE_ZEN_API_KEY` | -| OpenCode Go | API key | `OPENCODE_GO_API_KEY` | -| Qwen OAuth | OAuth | `hermes auth add qwen-oauth` | -| Custom endpoint | Config | `model.base_url` + `model.api_key` in config.yaml | -| GitHub Copilot ACP | External | `COPILOT_CLI_PATH` or Copilot CLI | - -Full provider docs: https://hermes-agent.nousresearch.com/docs/integrations/providers - -### Toolsets - -Enable/disable via `hermes tools` (interactive) or `hermes tools enable/disable NAME`. - -| Toolset | What it provides | -|---------|-----------------| -| `web` | Web search and content extraction | -| `search` | Web search only (subset of `web`) | -| `browser` | Browser automation (Browserbase, Camofox, or local Chromium) | -| `terminal` | Shell commands and process management | -| `file` | File read/write/search/patch | -| `code_execution` | Sandboxed Python execution | -| `vision` | Image analysis | -| `image_gen` | AI image generation | -| `video` | Video analysis and generation | -| `tts` | Text-to-speech | -| `skills` | Skill browsing and management | -| `memory` | Persistent cross-session memory | -| `session_search` | Search past conversations | -| `delegation` | Subagent task delegation | -| `cronjob` | Scheduled task management | -| `clarify` | Ask user clarifying questions | -| `messaging` | Cross-platform message sending | -| `todo` | In-session task planning and tracking | -| `kanban` | Multi-agent work-queue tools (gated to workers) | -| `debugging` | Extra introspection/debug tools (off by default) | -| `safe` | Minimal, low-risk toolset for locked-down sessions | -| `spotify` | Spotify playback and playlist control | -| `homeassistant` | Smart home control (off by default) | -| `discord` | Discord integration tools | -| `discord_admin` | Discord admin/moderation tools | -| `feishu_doc` | Feishu (Lark) document tools | -| `feishu_drive` | Feishu (Lark) drive tools | -| `yuanbao` | Yuanbao integration tools | -| `rl` | Reinforcement learning tools (off by default) | - -Full enumeration lives in `toolsets.py` as the `TOOLSETS` dict; `_HERMES_CORE_TOOLS` is the default bundle most platforms inherit from. - -Tool changes take effect on `/reset` (new session). They do NOT apply mid-conversation to preserve prompt caching. - ---- - -## Security & Privacy Toggles - -Common "why is Hermes doing X to my output / tool calls / commands?" toggles — and the exact commands to change them. Most of these need a fresh session (`/reset` in chat, or start a new `hermes` invocation) because they're read once at startup. - -### Secret redaction in tool output - -Secret redaction is **on by default** — tool output (terminal stdout, `read_file`, web content, subagent summaries, etc.) is scanned for strings that look like API keys, tokens, and secrets before it enters the conversation context and logs. Leave it enabled for normal use: - -```bash -hermes config set security.redact_secrets true # keep enabled globally -``` - -**Restart required.** `security.redact_secrets` is snapshotted at import time — toggling it mid-session (e.g. via `export HERMES_REDACT_SECRETS=false` from a tool call) will NOT take effect for the running process. Tell the user to change it in config from a terminal, then start a new session. This is deliberate — it prevents an LLM from flipping the toggle on itself mid-task. - -Disable only when you deliberately need raw credential-like strings for debugging or redactor development: -```bash -hermes config set security.redact_secrets false -``` - -### PII redaction in gateway messages - -Separate from secret redaction. When enabled, the gateway hashes user IDs and strips phone numbers from the session context before it reaches the model: - -```bash -hermes config set privacy.redact_pii true # enable -hermes config set privacy.redact_pii false # disable (default) -``` - -### Command approval prompts - -By default (`approvals.mode: smart`), Hermes asks an auxiliary LLM to assess shell commands flagged as destructive (`rm -rf`, `git reset --hard`, etc.). The modes are: - -- `smart` — auto-approve a low-risk command once, deny high-risk commands, and prompt when uncertain (default) -- `manual` — always prompt -- `off` — skip all approval prompts (equivalent to `--yolo`) - -```bash -hermes config set approvals.mode smart # recommended middle ground -hermes config set approvals.mode off # bypass everything (not recommended) -``` - -Per-invocation bypass without changing config: -- `hermes --yolo …` -- `export HERMES_YOLO_MODE=1` - -Note: YOLO / `approvals.mode: off` does NOT turn off secret redaction. They are independent. - -### Shell hooks allowlist - -Some shell-hook integrations require explicit allowlisting before they fire. Managed via `~/.hermes/shell-hooks-allowlist.json` — prompted interactively the first time a hook wants to run. - -### Disabling the web/browser/image-gen tools - -To keep the model away from network or media tools entirely, open `hermes tools` and toggle per-platform. Takes effect on next session (`/reset`). See the Tools & Skills section above. - ---- - -## Voice & Transcription - -### STT (Voice → Text) - -Voice messages from messaging platforms are auto-transcribed. - -Provider priority (auto-detected): -1. **Local faster-whisper** — free, no API key: `pip install faster-whisper` -2. **Groq Whisper** — free tier: set `GROQ_API_KEY` -3. **OpenAI Whisper** — paid: set `VOICE_TOOLS_OPENAI_KEY` -4. **Mistral Voxtral** — set `MISTRAL_API_KEY` - -Config: -```yaml -stt: - enabled: true - provider: local # local, groq, openai, mistral - local: - model: base # tiny, base, small, medium, large-v3 -``` - -### TTS (Text → Voice) - -| Provider | Env var | Free? | -|----------|---------|-------| -| Edge TTS | None | Yes (default) | -| ElevenLabs | `ELEVENLABS_API_KEY` | Free tier | -| OpenAI | `VOICE_TOOLS_OPENAI_KEY` | Paid | -| MiniMax | `MINIMAX_API_KEY` | Paid | -| Mistral (Voxtral) | `MISTRAL_API_KEY` | Paid | -| NeuTTS (local) | None (`pip install neutts[all]` + `espeak-ng`) | Free | - -Voice commands: `/voice on` (voice-to-voice), `/voice tts` (always voice), `/voice off`. - ---- +Two theming rules that hold even without loading the reference: **you apply skins yourself** (`hermes config set display.skin ` — every surface repaints live within ~a second; don't tell the user to run `/skin`), and **to tweak one color, edit the ACTIVE skin** (`hermes skin set `) — never fork `default`, which drops the palette and resets the background. ## Spawning Additional Hermes Instances @@ -633,429 +202,20 @@ terminal(command="tmux new-session -d -s resumed 'hermes --resume 20260225_14305 - **Use `hermes chat -q` for fire-and-forget** — no PTY needed - **Use tmux for interactive sessions** — raw PTY mode has `\r` vs `\n` issues with prompt_toolkit - **For scheduled tasks**, use the `cronjob` tool instead of spawning — handles delivery and retry +- **"delegate_task is capped at N" reports** — see `references/delegate-task-concurrency-diagnosis.md`. Three real cap paths in Hermes; if none fired, the model is self-limiting and rationalising it as "the runtime caps." +- **"Can $external_app use my Nous Portal subscription / OAuth?"** — see `references/portal-auth-for-third-party-apps.md`. Walk the user through three layers (plugin-vs-app, what Portal actually exposes, local-broker-proxy option). ---- +## Surfaces (quick orientation) -## Durable & Background Systems +- **Desktop app** (`hermes desktop` / `hermes gui`) — native Electron app for macOS/Linux/Windows: streaming chat, session list, Cmd+K palette, drag-and-drop files, native notifications, per-profile remote-gateway login. Extend it with UI plugins — `references/desktop-plugins.md`. +- **Web dashboard** (`hermes dashboard`) — full admin panel: messaging channels, MCP catalog, webhooks, memory, profile builder, plus an embedded `hermes --tui` chat. Secured behind an OAuth/token gate. +- **Ink TUI** (`hermes --tui` or `display.interface: tui`) — terminal UI with docked widget apps — `references/tui-widgets.md`. +- **OpenAI-compatible proxy** (`hermes proxy`) — a local OpenAI API backed by whichever OAuth provider you're signed into. Point Codex CLI, Aider, Cline, or any script at it — no API key. -Four systems run alongside the main conversation loop. Quick reference -here; full developer notes live in `AGENTS.md`, user-facing docs under -`website/docs/user-guide/features/`. +## Hard Invariants (never violate, regardless of what you loaded) -### Delegation (`delegate_task`) - -Synchronous subagent spawn — the parent waits for the child's summary -before continuing its own loop. Isolated context + terminal session. - -- **Single:** `delegate_task(goal, context)`. -- **Batch:** `delegate_task(tasks=[{goal, ...}, ...])` runs children in - parallel, capped by `delegation.max_concurrent_children` (default 3). -- **Roles:** `leaf` (default; cannot re-delegate) vs `orchestrator` - (can spawn its own workers, bounded by `delegation.max_spawn_depth`). -- **Not durable.** If the parent is interrupted, the child is - cancelled. For work that must outlive the turn, use `cronjob` or - `terminal(background=True, notify_on_complete=True)`. - -Config: `delegation.*` in `config.yaml`. - -### Cron (scheduled jobs) - -Durable scheduler — `cron/jobs.py` + `cron/scheduler.py`. Drive it via -the `cronjob` tool, the `hermes cron` CLI (`list`, `add`, `edit`, -`pause`, `resume`, `run`, `remove`), or the `/cron` slash command. - -- **Schedules:** duration (`"30m"`, `"2h"`), "every" phrase - (`"every monday 9am"`), 5-field cron (`"0 9 * * *"`), or ISO timestamp. -- **Per-job knobs:** `skills`, `model`/`provider` override, `script` - (pre-run data collection; `no_agent=True` makes the script the whole - job), `context_from` (chain job A's output into job B), `workdir` - (run in a specific dir with its `AGENTS.md` / `CLAUDE.md` loaded), - multi-platform delivery. -- **Invariants:** 3-minute hard interrupt per run, `.tick.lock` file - prevents duplicate ticks across processes, cron sessions pass - `skip_memory=True` by default, and cron deliveries are framed with a - header/footer instead of being mirrored into the target gateway - session (keeps role alternation intact). - -User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/cron - -### Curator (skill lifecycle) - -Background maintenance for agent-created skills. Tracks usage, marks -idle skills stale, archives stale ones, keeps a pre-run tar.gz backup -so nothing is lost. - -- **CLI:** `hermes curator ` — `status`, `run`, `pause`, `resume`, - `pin`, `unpin`, `archive`, `restore`, `prune`, `backup`, `rollback`. -- **Slash:** `/curator ` mirrors the CLI. -- **Scope:** only touches skills with `created_by: "agent"` provenance. - Bundled + hub-installed skills are off-limits. **Never deletes** — - max destructive action is archive. Pinned skills are exempt from - every auto-transition and every LLM review pass. -- **Telemetry:** sidecar at `~/.hermes/skills/.usage.json` holds - per-skill `use_count`, `view_count`, `patch_count`, - `last_activity_at`, `state`, `pinned`. - -Config: `curator.*` (`enabled`, `interval_hours`, `min_idle_hours`, -`stale_after_days`, `archive_after_days`, `backup.*`). -User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/curator - -### Kanban (multi-agent work queue) - -Durable SQLite board for multi-profile / multi-worker collaboration. -Users drive it via `hermes kanban `; dispatcher-spawned workers -see a focused `kanban_*` toolset gated by `HERMES_KANBAN_TASK`, and -orchestrator profiles can opt into the broader `kanban` toolset. Normal -sessions still have zero `kanban_*` schema footprint unless configured. - -- **CLI verbs (common):** `init`, `create`, `list` (alias `ls`), - `show`, `assign`, `link`, `unlink`, `comment`, `complete`, `block`, - `unblock`, `archive`, `tail`. Less common: `watch`, `stats`, `runs`, - `log`, `dispatch`, `daemon`, `gc`. -- **Worker/orchestrator toolset:** `kanban_show`, `kanban_complete`, - `kanban_block`, `kanban_heartbeat`, `kanban_comment`, `kanban_create`, - `kanban_link`; profiles that explicitly enable the `kanban` toolset - outside a dispatcher-spawned task also get `kanban_list` and - `kanban_unblock` for board routing. -- **Dispatcher** runs inside the gateway by default - (`kanban.dispatch_in_gateway: true`) — reclaims stale claims, - promotes ready tasks, atomically claims, spawns assigned profiles. - Auto-blocks a task after `failure_limit` consecutive spawn failures - (default 2; configurable via `kanban.failure_limit` or per-task - `max_retries`). -- **Isolation:** board is the hard boundary (workers get - `HERMES_KANBAN_BOARD` pinned in env); tenant is a soft namespace - within a board for workspace-path + memory-key isolation. - -User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban - ---- - -## Windows-Specific Quirks - -Hermes runs natively on Windows (PowerShell, cmd, Windows Terminal, git-bash -mintty, VS Code integrated terminal). Most of it just works, but a handful -of differences between Win32 and POSIX have bitten us — document new ones -here as you hit them so the next person (or the next session) doesn't -rediscover them from scratch. - -### Input / Keybindings - -**Alt+Enter doesn't insert a newline.** Windows Terminal intercepts Alt+Enter -at the terminal layer to toggle fullscreen — the keystroke never reaches -prompt_toolkit. Use **Ctrl+Enter** instead. Windows Terminal delivers -Ctrl+Enter as LF (`c-j`), distinct from plain Enter (`c-m` / CR), and the -CLI binds `c-j` to newline insertion on `win32` only (see -`_bind_prompt_submit_keys` + the Windows-only `c-j` binding in `cli.py`). -Side effect: the raw Ctrl+J keystroke also inserts a newline on Windows — -unavoidable, because Windows Terminal collapses Ctrl+Enter and Ctrl+J to -the same keycode at the Win32 console API layer. No conflicting binding -existed for Ctrl+J on Windows, so this is a harmless side effect. - -mintty / git-bash behaves the same (fullscreen on Alt+Enter) unless you -disable Alt+Fn shortcuts in Options → Keys. Easier to just use Ctrl+Enter. - -**Diagnosing keybindings.** Run `python scripts/keystroke_diagnostic.py` -(repo root) to see exactly how prompt_toolkit identifies each keystroke -in the current terminal. Answers questions like "does Shift+Enter come -through as a distinct key?" (almost never — most terminals collapse it -to plain Enter) or "what byte sequence is my terminal sending for -Ctrl+Enter?" This is how the Ctrl+Enter = c-j fact was established. - -### Config / Files - -**HTTP 400 "No models provided" on first run.** `config.yaml` was saved -with a UTF-8 BOM (common when Windows apps write it). Re-save as UTF-8 -without BOM. `hermes config edit` writes without BOM; manual edits in -Notepad are the usual culprit. - -### `execute_code` / Sandbox - -**WinError 10106** ("The requested service provider could not be loaded -or initialized") from the sandbox child process — it can't create an -`AF_INET` socket, so the loopback-TCP RPC fallback fails before -`connect()`. Root cause is usually **not** a broken Winsock LSP; it's -Hermes's own env scrubber dropping `SYSTEMROOT` / `WINDIR` / `COMSPEC` -from the child env. Python's `socket` module needs `SYSTEMROOT` to locate -`mswsock.dll`. Fixed via the `_WINDOWS_ESSENTIAL_ENV_VARS` allowlist in -`tools/code_execution_tool.py`. If you still hit it, echo `os.environ` -inside an `execute_code` block to confirm `SYSTEMROOT` is set. Full -diagnostic recipe in `references/execute-code-sandbox-env-windows.md`. - -### Testing / Contributing - -**`scripts/run_tests.sh` doesn't work as-is on Windows** — it looks for -POSIX venv layouts (`.venv/bin/activate`). The Hermes-installed venv at -`venv/Scripts/` has no pip or pytest either (stripped for install size). -Workaround: install `pytest + pytest-xdist + pyyaml` into a system Python -3.11 user site, then invoke pytest directly with `PYTHONPATH` set: - -```bash -"/c/Program Files/Python311/python" -m pip install --user pytest pytest-xdist pyyaml -export PYTHONPATH="$(pwd)" -"/c/Program Files/Python311/python" -m pytest tests/foo/test_bar.py -v --tb=short -n 0 -``` - -Use `-n 0`, not `-n 4` — `pyproject.toml`'s default `addopts` already -includes `-n`, and the wrapper's CI-parity guarantees don't apply off POSIX. - -**POSIX-only tests need skip guards.** Common markers already in the codebase: -- Symlinks — elevated privileges on Windows -- `0o600` file modes — POSIX mode bits not enforced on NTFS by default -- `signal.SIGALRM` — Unix-only (see `tests/conftest.py::_enforce_test_timeout`) -- Winsock / Windows-specific regressions — `@pytest.mark.skipif(sys.platform != "win32", ...)` - -Use the existing skip-pattern style (`sys.platform == "win32"` or -`sys.platform.startswith("win")`) to stay consistent with the rest of the -suite. - -### Path / Filesystem - -**Line endings.** Git may warn `LF will be replaced by CRLF the next time -Git touches it`. Cosmetic — the repo's `.gitattributes` normalizes. Don't -let editors auto-convert committed POSIX-newline files to CRLF. - -**Forward slashes work almost everywhere.** `C:/Users/...` is accepted by -every Hermes tool and most Windows APIs. Prefer forward slashes in code -and logs — avoids shell-escaping backslashes in bash. - ---- - -## Troubleshooting - -### Voice not working -1. Check `stt.enabled: true` in config.yaml -2. Verify provider: `pip install faster-whisper` or set API key -3. In gateway: `/restart`. In CLI: exit and relaunch. - -### Tool not available -1. `hermes tools` — check if toolset is enabled for your platform -2. Some tools need env vars (check `.env`) -3. `/reset` after enabling tools - -### Model/provider issues -1. `hermes doctor` — check config and dependencies -2. `hermes auth` — re-authenticate OAuth providers (or `hermes auth add `) -3. Check `.env` has the right API key -4. **Copilot 403**: `gh auth login` tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via `hermes model` → GitHub Copilot. - -### Changes not taking effect -- **Tools/skills:** `/reset` starts a new session with updated toolset -- **Config changes:** In gateway: `/restart`. In CLI: exit and relaunch. -- **Code changes:** Restart the CLI or gateway process - -### Skills not showing -1. `hermes skills list` — verify installed -2. `hermes skills config` — check platform enablement -3. Load explicitly: `/skill name` or `hermes -s name` - -### Gateway issues -Check logs first: -```bash -grep -i "failed to send\|error" ~/.hermes/logs/gateway.log | tail -20 -``` - -Common gateway problems: -- **Gateway dies on SSH logout**: Enable linger: `sudo loginctl enable-linger $USER` -- **Gateway dies on WSL2 close**: WSL2 requires `systemd=true` in `/etc/wsl.conf` for systemd services to work. Without it, gateway falls back to `nohup` (dies when session closes). -- **Gateway crash loop**: Reset the failed state: `systemctl --user reset-failed hermes-gateway` - -### Platform-specific issues -- **Discord bot silent**: Must enable **Message Content Intent** in Bot → Privileged Gateway Intents. -- **Slack bot only works in DMs**: Must subscribe to `message.channels` event. Without it, the bot ignores public channels. -- **Windows-specific issues** (`Alt+Enter` newline, WinError 10106, UTF-8 BOM config, test suite, line endings): see the dedicated **Windows-Specific Quirks** section above. - -### Auxiliary models not working -If `auxiliary` tasks (vision, compression, session_search) fail silently, the `auto` provider can't find a backend. Either set `OPENROUTER_API_KEY` or `GOOGLE_API_KEY`, or explicitly configure each auxiliary task's provider: -```bash -hermes config set auxiliary.vision.provider -hermes config set auxiliary.vision.model -``` - ---- -### Context window shows wrong size - -If Hermes reports a smaller context window than your local model supports -(e.g., 128k when llama-server has `-c 262144`): - -**Check if `model.context_length` is explicitly set.** Hermes uses a -multi-source resolution chain (highest priority first): - -1. `model.context_length` in config.yaml — **blocks auto-detection if set** -2. Custom provider per-model setting -3. Persistent cache (survives restarts) -4. `/v1/models` endpoint from your server — auto-detected when nothing - above overrides it - -**Fix:** Clear the override so auto-detection falls through: - - -## Where to Find Things - -| Looking for... | Location | -|----------------|----------| -| Config options | `hermes config edit` or [Configuration docs](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) | -| Available tools | `hermes tools list` or [Tools reference](https://hermes-agent.nousresearch.com/docs/reference/tools-reference) | -| Slash commands | `/help` in session or [Slash commands reference](https://hermes-agent.nousresearch.com/docs/reference/slash-commands) | -| Skills catalog | `hermes skills browse` or [Skills catalog](https://hermes-agent.nousresearch.com/docs/reference/skills-catalog) | -| Provider setup | `hermes model` or [Providers guide](https://hermes-agent.nousresearch.com/docs/integrations/providers) | -| Platform setup | `hermes gateway setup` or [Messaging docs](https://hermes-agent.nousresearch.com/docs/user-guide/messaging/) | -| MCP servers | `hermes mcp list` or [MCP guide](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp) | -| Profiles | `hermes profile list` or [Profiles docs](https://hermes-agent.nousresearch.com/docs/user-guide/profiles) | -| Cron jobs | `hermes cron list` or [Cron docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron) | -| Memory | `hermes memory status` or [Memory docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) | -| Env variables | `hermes config env-path` or [Env vars reference](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) | -| CLI commands | `hermes --help` or [CLI reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands) | -| Gateway logs | `~/.hermes/logs/gateway.log` | -| Session files | `hermes sessions browse` (reads state.db) | -| Source code | `~/.hermes/hermes-agent/` | - ---- - -## Contributor Quick Reference - -For occasional contributors and PR authors. Full developer docs: https://hermes-agent.nousresearch.com/docs/developer-guide/ - -### Project Layout - - -``` -hermes-agent/ -├── run_agent.py # AIAgent — core conversation loop -├── model_tools.py # Tool discovery and dispatch -├── toolsets.py # Toolset definitions -├── cli.py # Interactive CLI (HermesCLI) -├── hermes_state.py # SQLite session store -├── agent/ # Prompt builder, context compression, memory, model routing, credential pooling, skill dispatch -├── hermes_cli/ # CLI subcommands, config, setup, commands -│ ├── commands.py # Slash command registry (CommandDef) -│ ├── config.py # DEFAULT_CONFIG, env var definitions -│ └── main.py # CLI entry point and argparse -├── tools/ # One file per tool -│ └── registry.py # Central tool registry -├── gateway/ # Messaging gateway -│ └── platforms/ # Platform adapters (telegram, discord, etc.) -├── cron/ # Job scheduler -├── tests/ # ~3000 pytest tests -└── website/ # Docusaurus docs site -``` - - -Config: `~/.hermes/config.yaml` (settings), `~/.hermes/.env` (API keys) — both under `$HERMES_HOME` when it is set. - -### Adding a Tool (3 files) - -**1. Create `tools/your_tool.py`:** -```python -import json, os -from tools.registry import registry - -def check_requirements() -> bool: - return bool(os.getenv("EXAMPLE_API_KEY")) - -def example_tool(param: str, task_id: str = None) -> str: - return json.dumps({"success": True, "data": "..."}) - -registry.register( - name="example_tool", - toolset="example", - schema={"name": "example_tool", "description": "...", "parameters": {...}}, - handler=lambda args, **kw: example_tool( - param=args.get("param", ""), task_id=kw.get("task_id")), - check_fn=check_requirements, - requires_env=["EXAMPLE_API_KEY"], -) -``` - -**2. Add to `toolsets.py`** → `_HERMES_CORE_TOOLS` list. - -Auto-discovery: any `tools/*.py` file with a top-level `registry.register()` call is imported automatically — no manual list needed. - -All handlers must return JSON strings. Use `get_hermes_home()` for paths, never hardcode `~/.hermes`. - -### Adding a Slash Command - -1. Add `CommandDef` to `COMMAND_REGISTRY` in `hermes_cli/commands.py` -2. Add handler in `cli.py` → `process_command()` -3. (Optional) Add gateway handler in `gateway/run.py` - -All consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically. - -### Agent Loop (High Level) - -``` -run_conversation(): - 1. Build system prompt - 2. Loop while iterations < max: - a. Call LLM (OpenAI-format messages + tool schemas) - b. If tool_calls → dispatch each via handle_function_call() → append results → continue - c. If text response → return - 3. Context compression triggers automatically near token limit -``` - -### Testing - -```bash -python -m pytest tests/ -o 'addopts=' -q # Full suite -python -m pytest tests/tools/ -q # Specific area -``` - -- Tests auto-redirect `HERMES_HOME` to temp dirs — never touch real `~/.hermes/` -- Run full suite before pushing any change -- Use `-o 'addopts='` to clear any baked-in pytest flags - -**Windows contributors:** `scripts/run_tests.sh` currently looks for POSIX venvs (`.venv/bin/activate` / `venv/bin/activate`) and will error out on Windows where the layout is `venv/Scripts/activate` + `python.exe`. The Hermes-installed venv at `venv/Scripts/` also has no `pip` or `pytest` — it's stripped for end-user install size. Workaround: install pytest + pytest-xdist + pyyaml into a system Python 3.11 user site (`/c/Program Files/Python311/python -m pip install --user pytest pytest-xdist pyyaml`), then run tests directly: - -```bash -export PYTHONPATH="$(pwd)" -"/c/Program Files/Python311/python" -m pytest tests/tools/test_foo.py -v --tb=short -n 0 -``` - -Use `-n 0` (not `-n 4`) because `pyproject.toml`'s default `addopts` already includes `-n`, and the wrapper's CI-parity story doesn't apply off-POSIX. - -**Cross-platform test guards:** tests that use POSIX-only syscalls need a skip marker. Common ones already in the codebase: -- Symlink creation → `@pytest.mark.skipif(sys.platform == "win32", reason="Symlinks require elevated privileges on Windows")` (see `tests/cron/test_cron_script.py`) -- POSIX file modes (0o600, etc.) → `@pytest.mark.skipif(sys.platform.startswith("win"), reason="POSIX mode bits not enforced on Windows")` (see `tests/hermes_cli/test_auth_toctou_file_modes.py`) -- `signal.SIGALRM` → Unix-only (see `tests/conftest.py::_enforce_test_timeout`) -- Live Winsock / Windows-specific regression tests → `@pytest.mark.skipif(sys.platform != "win32", reason="Windows-specific regression")` - -**Monkeypatching `sys.platform` is not enough** when the code under test also calls `platform.system()` / `platform.release()` / `platform.mac_ver()`. Those functions re-read the real OS independently, so a test that sets `sys.platform = "linux"` on a Windows runner will still see `platform.system() == "Windows"` and route through the Windows branch. Patch all three together: - -```python -monkeypatch.setattr(sys, "platform", "linux") -monkeypatch.setattr(platform, "system", lambda: "Linux") -monkeypatch.setattr(platform, "release", lambda: "6.8.0-generic") -``` - -See `tests/agent/test_prompt_builder.py::TestEnvironmentHints` for a worked example. - -### Extending the system prompt's execution-environment block - -Factual guidance about the host OS, user home, cwd, terminal backend, and shell (bash vs. PowerShell on Windows) is emitted from `agent/prompt_builder.py::build_environment_hints()`. This is also where the WSL hint and per-backend probe logic live. The convention: - -- **Local terminal backend** → emit host info (OS, `$HOME`, cwd) + Windows-specific notes (hostname ≠ username, `terminal` uses bash not PowerShell). -- **Remote terminal backend** (anything in `_REMOTE_TERMINAL_BACKENDS`: `docker, singularity, modal, daytona, ssh, managed_modal`) → **suppress** host info entirely and describe only the backend. A live `uname`/`whoami`/`pwd` probe runs inside the backend via `tools.environments.get_environment(...).execute(...)`, cached per process in `_BACKEND_PROBE_CACHE`, with a static fallback if the probe times out. -- **Key fact for prompt authoring:** when `TERMINAL_ENV != "local"`, *every* file tool (`read_file`, `write_file`, `patch`, `search_files`) runs inside the backend container, not on the host. The system prompt must never describe the host in that case — the agent can't touch it. - -Full design notes, the exact emitted strings, and testing pitfalls: -`references/prompt-builder-environment-hints.md`. - -**Refactor-safety pattern (POSIX-equivalence guard):** when you extract inline logic into a helper that adds Windows/platform-specific behavior, keep a `_legacy_` oracle function in the test file that's a verbatim copy of the old code, then parametrize-diff against it. Example: `tests/tools/test_code_execution_windows_env.py::TestPosixEquivalence`. This locks in the invariant that POSIX behavior is bit-for-bit identical and makes any future drift fail loudly with a clear diff. - -### Commit Conventions - -``` -type: concise subject line - -Optional body. -``` - -Types: `fix:`, `feat:`, `refactor:`, `docs:`, `chore:` - -### Key Rules - -- **Never break prompt caching** — don't change context, tools, or system prompt mid-conversation -- **Message role alternation** — never two assistant or two user messages in a row -- Use `get_hermes_home()` from `hermes_constants` for all paths (profile-safe) -- Config values go in `config.yaml`, secrets go in `.env` -- New tools need a `check_fn` so they only appear when requirements are met +- **Never break prompt caching** — don't change past context, toolsets, or the system prompt mid-conversation. The only exception is context compression. +- **Message role alternation** — never two assistant or two user messages in a row; only `tool` results can repeat. +- **Secrets in `.env`, settings in `config.yaml`** — never tell a user to put a non-credential setting in `.env`. +- **Profile-safe paths** — `get_hermes_home()` in code, `$HERMES_HOME` when resolving paths in a session. +- **Never hand-edit `config.yaml` for the user** — use `hermes config set KEY VAL`; a stray indent can corrupt the file and break the live gateway. diff --git a/website/docs/user-guide/skills/bundled/hermes-desktop-plugins/hermes-desktop-plugins-hermes-desktop-plugins.md b/website/docs/user-guide/skills/bundled/hermes-desktop-plugins/hermes-desktop-plugins-hermes-desktop-plugins.md deleted file mode 100644 index af0015b7983d..000000000000 --- a/website/docs/user-guide/skills/bundled/hermes-desktop-plugins/hermes-desktop-plugins-hermes-desktop-plugins.md +++ /dev/null @@ -1,180 +0,0 @@ ---- -title: "Hermes Desktop Plugins — Write desktop app plugins that add UI panes and commands" -sidebar_label: "Hermes Desktop Plugins" -description: "Write desktop app plugins that add UI panes and commands" ---- - -{/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */} - -# Hermes Desktop Plugins - -Write desktop app plugins that add UI panes and commands. - -## Skill metadata - -| | | -|---|---| -| Source | Bundled (installed by default) | -| Path | `skills/hermes-desktop-plugins` | -| Version | `1.0.0` | -| Platforms | linux, macos, windows | -| Tags | `desktop`, `plugins`, `ui`, `extension` | - -## Reference: full SKILL.md - -:::info -The following is the complete skill definition that Hermes loads when this skill is triggered. This is what the agent sees as instructions when the skill is active. -::: - -# Hermes Desktop Plugins Skill - -Write plugins for the Hermes desktop app: statusbar items, layout panes, -command-palette commands, keybinds, routes, and themes. A plugin is a single -plain-JavaScript ESM file the app loads at runtime — no build step, no repo -changes. A plugin can also talk to its own Python backend namespace -(`ctx.rest`/`ctx.socket` → `/api/plugins/`); the general Python plugin -system (`~/.hermes/plugins/`) is otherwise documented separately. - -Full human reference (every export, area payloads, backend, security): -`website/docs/developer-guide/desktop-plugin-sdk.md`. - -## When to Use - -- The user asks for a new desktop UI element (a pane, a statusbar widget, a - dashboard, a command) without modifying the app itself. -- You want to surface data you compute (via gateway RPC) inside the app. - -## Prerequisites - -- The Hermes desktop app (it loads plugins; the CLI/gateway alone does not). -- Write access to `$HERMES_HOME/desktop-plugins/` (usually - `~/.hermes/desktop-plugins/`). - -## How to Run - -1. Create `$HERMES_HOME/desktop-plugins//plugin.js` from - `templates/plugin.js` (relative to this skill directory) — that's - `~/.hermes/...` by default, or `~/.hermes/profiles//...` under a - named profile. Keep `` equal to the plugin `id`. -2. The desktop app watches that directory: the plugin loads within a few - seconds of the file landing, and every later save hot-reloads it in - place. No reload step. (Fallback if it doesn't appear: ⌘K → - **Reload desktop plugins**.) -3. If loading fails the app shows a toast naming the error — fix the file - and save again. - -## Quick Reference - -The ONLY import surface is `@hermes/plugin-sdk` (plus `react` / -`react/jsx-runtime`, which resolve to the app's own React — write UI with -`jsx()` calls, not JSX syntax; the file is not compiled). - -- `host.state.*` — readonly reactive atoms: `activeSessionId`, `cwd`, - `gateway`, `model`, `profile`, `viewport`. Read with `.get()` in handlers, - `useValue(atom)` in components. -- `host.request(method, params)` — gateway JSON-RPC (sessions, config, - skills, cron — everything the app uses). -- `host.onEvent(type, fn)` — live gateway events (`'*'` for all). Returns a - disposer. -- `host.notify({ kind, message })`, `host.navigate(path)`, `host.logs(...)`, - `host.status()`, `haptic('tap')`. -- `ctx.register({ id, area, order?, render?, data? })` — contribute UI. - Key areas: `'statusBar.right'`/`'statusBar.left'` (chips), - `'panes'` (layout zones — set `title` and - `data: { placement, dock?, width?, height? }`; the pane auto-joins a - matching zone), `PALETTE_AREA` (⌘K commands), `KEYBINDS_AREA` (rebindable - actions). -- Pane placement: `placement: 'left'|'right'|'bottom'|'main'` is the - semantic role — the pane stacks (tabs) with existing panes of that role. - To land on a specific EDGE instead, add `dock: { pane, pos }` — the same - gesture as dragging onto a pane's drop chip. `pane` is any pane id - (`workspace` is the main thread; also `sessions`, `terminal`, `files`, - `review`, `logs`), `pos` is `'top'|'bottom'|'left'|'right'|'center'`. - E.g. "below the conversation" = `dock: { pane: 'workspace', pos: 'bottom' }` - — declare a `height` (e.g. `'200px'`) so it doesn't take half the zone. -- Full PAGES: register `area: ROUTES_AREA` with `data: { path: '/my-page' }` - and a `render` — the page mounts in the workspace (main) pane like any - built-in view. Make it reachable with a sidebar nav row: - `ctx.register({ id: 'nav', area: SIDEBAR_NAV_AREA, data: { path: '/my-page', label: 'My Page', codicon: 'project' } })` - (renders below Artifacts, lights up at the route) — and/or a - `PALETTE_AREA` command calling `host.navigate('/my-page')`. -- `ctx.storage.get/set/remove` — persistence namespaced to your plugin. -- `ctx.i18n.register({ en, ja, ... })` — ship your OWN locale bundles, scoped - to your plugin (never edit core `en.ts`). Values are literal strings or - interpolator functions; nested trees are addressed by dot-path. Read them - reactively in components with `usePluginI18n(id)` returning `t('key', ...args)` - (re-renders on a locale switch), or via `ctx.i18n.t` in handlers/stores. - Resolution follows the app's active locale, then your `en`, then the raw key. -- Data: `useQuery`/`useMutation`/`useQueryClient`/`queryClient` (the app's ONE - React Query client — cache, dedupe, `refetchInterval`, invalidate like core; - never hand-roll a poll loop), plus `atom`/`computed` for plugin-local state. -- Backend: if the plugin ships a Python `plugin_api.py` (under - `~/.hermes/plugins//dashboard/`, manifest `"api": "plugin_api.py"`), reach - it with `ctx.rest('/path', { method?, body?, timeoutMs? })` and its live twin - `ctx.socket('/events', onMessage)` — both scoped to `/api/plugins/` by - construction (traversal rejected). `ctx.socket` is a **no-op on OAuth - remotes**, so always keep a polling fallback. The Python backend is imported - only when the plugin is in `plugins.enabled` in `config.yaml` (separate from - the in-app enable toggle). For gateway-wide data use `host.request` / - `host.onEvent` instead. -- `Contribute` (mount-scoped): render `jsx(Contribute, { area, id, children })` - inside a component so page-owned chrome (e.g. a titlebar control in - `TITLEBAR_AREAS.center`) leaves when the page unmounts — `ctx.register` is for - permanent contributions. -- `defaultEnabled: false` on the default export ships an opt-in plugin: it - inventories in Settings → Plugins, off until the user flips it on. -- Users manage plugins in Settings → Plugins (enable/disable live, reveal - folder). A disabled plugin stays disabled across restarts — don't fight - it; the user turned you off. -- UI: the app's design language, importable directly — `Button`, `Input`, - `Textarea`, `Select*`, `Switch`, `Checkbox`, `SegmentedControl`, `Tabs*`, - `Dialog*`, `ConfirmDialog`, `DropdownMenu*`, `ContextMenu*`, `Popover*`, - `Tip`/`Tooltip*`, `Badge`, `Kbd`/`KbdGroup`, `SearchField`, `ScrollArea`, - `Separator`, `Skeleton`, `GlyphSpinner`, `EmptyState`, `ErrorState`, - `CopyButton`, `StatusDot`, `LogView`, `Codicon`, `DecodeText`, plus `cn` - and `icons.*`. Prefer these over hand-rolled elements so the plugin looks - native; style with theme vars, never hardcoded colors. - -## Procedure - -1. Pick a short kebab-case `id`; the folder name must match. -2. Start from `templates/plugin.js`; keep the default export shape - (`{ id, name, register(ctx) }`). -3. For a pane, register `area: 'panes'` with a `placement` hint and a - `render` returning your component — the app places it into a sensible - zone automatically; the user can drag it anywhere afterwards. -4. Fetch data with `host.request` and/or subscribe with `host.onEvent`; - never poll faster than a few seconds. -5. Write the file with your file tools, then ask the user to run - **Reload desktop plugins** from ⌘K. - -## Pitfalls - -- NEVER hardcode colors or backgrounds (`#000`, `black`, `rgb(...)`). Panes - already sit on the app's editor background — leave the background alone - and use theme variables for everything else: `var(--ui-text-secondary)`, - `var(--ui-text-quaternary)`, `var(--ui-stroke-secondary)`, - `var(--ui-accent)`. For canvas drawing, resolve them once with - `getComputedStyle(canvas).getPropertyValue('--ui-accent')`. -- Reference only what you imported — a component you forgot to import - (e.g. `StatusDot`) is a ReferenceError at render. Double-check every - identifier in your `jsx()` calls appears in the import line. -- Canvas panes MUST track their container with a `ResizeObserver` and - re-size the canvas (width/height attributes, not just CSS) — panes resize - constantly (sash drags, layout switches); a mount-time-only size leaves - blank space or blurry scaling. -- JSX syntax will not parse — the file loads uncompiled. Use - `jsx('div', { children: ... })` from `react/jsx-runtime`. -- Do not import anything except `@hermes/plugin-sdk`, `react`, and - `react/jsx-runtime`; other specifiers fail to resolve. -- Handlers must read state imperatively (`$atom.get()`), never from render - closures — rapid events will otherwise see stale values. -- Keep components small; subscribe (`useValue`) only in the leaf that - renders the value. - -## Verification - -- The plugin's UI appears after **Reload desktop plugins**. -- No error toast ("Plugin <name> failed to load") appears; if it does, the - message names the failure — fix and reload. -- For panes: the new zone is visible and draggable like any core pane. diff --git a/website/docs/user-guide/skills/bundled/productivity/productivity-petdex.md b/website/docs/user-guide/skills/bundled/productivity/productivity-petdex.md deleted file mode 100644 index 56ed48d0886f..000000000000 --- a/website/docs/user-guide/skills/bundled/productivity/productivity-petdex.md +++ /dev/null @@ -1,105 +0,0 @@ ---- -title: "Petdex — Install and select animated petdex mascots for Hermes" -sidebar_label: "Petdex" -description: "Install and select animated petdex mascots for Hermes" ---- - -{/* This page is auto-generated from the skill's SKILL.md by website/scripts/generate-skill-docs.py. Edit the source SKILL.md, not this page. */} - -# Petdex - -Install and select animated petdex mascots for Hermes. - -## Skill metadata - -| | | -|---|---| -| Source | Bundled (installed by default) | -| Path | `skills/productivity/petdex` | -| Version | `1.0.0` | -| Author | Hermes Agent | -| License | MIT | -| Platforms | linux, macos, windows | -| Tags | `petdex`, `mascot`, `display`, `cli`, `tui`, `desktop` | - -## Reference: full SKILL.md - -:::info -The following is the complete skill definition that Hermes loads when this skill is triggered. This is what the agent sees as instructions when the skill is active. -::: - -# Petdex Skill - -Browse, install, and select animated "pet" mascots from the public -[petdex](https://github.com/crafter-station/petdex) gallery. An installed pet -reacts to agent activity (idle, running a tool, reviewing, error, done) across -the Hermes CLI, TUI, and desktop app. This skill drives the `hermes pets` CLI -and the `display.pet` config — it does not generate sprites. - -## When to Use - -- The user wants a desktop/terminal mascot or asks about "pets" / petdex. -- The user wants to change, preview, or disable the active pet. -- Diagnosing why a pet isn't showing (terminal graphics support, config). - -## Prerequisites - -- Network access to `petdex.dev` for the gallery/manifest (read-only, no auth). -- Pillow (a core Hermes dependency) for sprite decoding — already installed. -- For full-fidelity terminal rendering: a graphics-capable terminal (kitty, - Ghostty, WezTerm, iTerm2, or sixel). Otherwise a truecolor Unicode - half-block fallback is used automatically. - -## How to Run - -Use the `terminal` tool to run `hermes pets `. - -## Quick Reference - -| Goal | Command | -| --- | --- | -| Browse the gallery | `hermes pets list` (add a substring to filter: `hermes pets list cat`) | -| List installed pets | `hermes pets list --installed` | -| Install a pet | `hermes pets install ` (add `--select` to make it active) | -| Set the active pet | `hermes pets select ` (omit slug for a picker) | -| Resize the pet everywhere | `hermes pets scale ` (e.g. `0.5`, clamped 0.1–3.0) | -| Preview/animate in terminal | `hermes pets show [slug] [--cycle] [--state run]` | -| Disable the pet | `hermes pets off` | -| Remove a pet | `hermes pets remove ` | -| Diagnose setup | `hermes pets doctor` | - -## Procedure - -1. Find a pet: `hermes pets list ` and note its `slug`. -2. Install + activate: `hermes pets install --select`. -3. Preview it: `hermes pets show` (Ctrl+C to stop). -4. Confirm setup: `hermes pets doctor` — shows the resolved pet, configured - render mode, detected terminal graphics protocol, and effective mode. - -Pets install into `/pets//` (profile-aware). Selecting a pet -writes `display.pet.slug` + `display.pet.enabled` to `config.yaml`. - -## Configuration - -Under `display.pet` in `config.yaml`: - -- `enabled` (bool) — master on/off. -- `slug` (str) — active pet; empty = first installed. -- `render_mode` — `auto` (detect) | `kitty` | `iterm` | `sixel` | `unicode` | `off`. -- `scale` (float) — on-screen size of the native 192×208 frames (default 0.33, - clamped 0.1–3.0). One knob resizes every surface; set it with - `hermes pets scale `, the `/pet scale` slash command, or the desktop - Appearance slider. -- `unicode_cols` (int) — width in columns for the Unicode fallback. - -## Pitfalls - -- A pet only shows once one is installed AND selected (`enabled: true`). -- Inside a pipe/redirect (no TTY) terminal rendering is disabled by design. -- The petdex npm CLI installs to `~/.codex/pets`; Hermes uses its own - profile-scoped `/pets/` instead — install through `hermes pets`. - -## Verification - -- `hermes pets doctor` reports `✓ ready` when a pet is installed, selected, - enabled, and Pillow is importable. diff --git a/website/sidebars.ts b/website/sidebars.ts index f306b07a81ee..1e7802cca51a 100644 --- a/website/sidebars.ts +++ b/website/sidebars.ts @@ -214,15 +214,6 @@ const sidebars: SidebarsConfig = { 'user-guide/skills/bundled/github/github-github-repo-management', ], }, - { - type: 'category', - label: 'hermes-desktop-plugins', - key: 'skills-bundled-hermes-desktop-plugins', - collapsed: true, - items: [ - 'user-guide/skills/bundled/hermes-desktop-plugins/hermes-desktop-plugins-hermes-desktop-plugins', - ], - }, { type: 'category', label: 'media', @@ -273,7 +264,6 @@ const sidebars: SidebarsConfig = { 'user-guide/skills/bundled/productivity/productivity-notion', 'user-guide/skills/bundled/productivity/productivity-ocr-and-documents', 'user-guide/skills/bundled/productivity/productivity-pdf', - 'user-guide/skills/bundled/productivity/productivity-petdex', 'user-guide/skills/bundled/productivity/productivity-powerpoint', 'user-guide/skills/bundled/productivity/productivity-teams-meeting-pipeline', 'user-guide/skills/bundled/productivity/productivity-xlsx',