mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-26 01:01:40 +00:00
docs: expand Docusaurus coverage across CLI, tools, skills, and skins (#1232)
- add code-derived reference pages for slash commands, tools, toolsets, bundled skills, and official optional skills - document the skin system and link visual theming separately from conversational personality - refresh quickstart, configuration, environment variable, and messaging docs to match current provider, gateway, and browser behavior - fix stale command, session, and Home Assistant configuration guidance
This commit is contained in:
Teknium
GitHub
parent
2bf6b7ad1a
commit
984f00e0b0
26 changed files with 1228 additions and 397 deletions
|
|
@ -94,7 +94,7 @@ Entries can optionally include:
|
|||
|
||||
Each prompt gets a randomly sampled set of toolsets from a **distribution**. This ensures training data covers diverse tool combinations. Use `--list_distributions` to see all available distributions.
|
||||
|
||||
Distributions define probability weights for each toolset combination. For example, a "default" distribution might assign high probability to `["terminal", "file", "web"]` and lower probability to web-only or file-only combinations.
|
||||
In the current implementation, distributions assign a probability to **each individual toolset**. The sampler flips each toolset independently, then guarantees that at least one toolset is enabled. This is different from a hand-authored table of prebuilt combinations.
|
||||
|
||||
## Output Format
|
||||
|
||||
|
|
|
|||
|
|
@ -7,11 +7,16 @@ sidebar_position: 5
|
|||
|
||||
# Browser Automation
|
||||
|
||||
Hermes Agent includes a full browser automation toolset powered by [Browserbase](https://browserbase.com), enabling the agent to navigate websites, interact with page elements, fill forms, and extract information — all running in cloud-hosted browsers with built-in anti-bot stealth features.
|
||||
Hermes Agent includes a full browser automation toolset that can run in two modes:
|
||||
|
||||
- **Browserbase cloud mode** via [Browserbase](https://browserbase.com) for managed cloud browsers and anti-bot tooling
|
||||
- **Local browser mode** via the `agent-browser` CLI and a local Chromium installation
|
||||
|
||||
In both modes, the agent can navigate websites, interact with page elements, fill forms, and extract information.
|
||||
|
||||
## Overview
|
||||
|
||||
The browser tools use the `agent-browser` CLI with Browserbase cloud execution. Pages are represented as **accessibility trees** (text-based snapshots), making them ideal for LLM agents. Interactive elements get ref IDs (like `@e1`, `@e2`) that the agent uses for clicking and typing.
|
||||
The browser tools use the `agent-browser` CLI. In Browserbase mode, `agent-browser` connects to Browserbase cloud sessions. In local mode, it drives a local Chromium installation. Pages are represented as **accessibility trees** (text-based snapshots), making them ideal for LLM agents. Interactive elements get ref IDs (like `@e1`, `@e2`) that the agent uses for clicking and typing.
|
||||
|
||||
Key capabilities:
|
||||
|
||||
|
|
@ -23,16 +28,22 @@ Key capabilities:
|
|||
|
||||
## Setup
|
||||
|
||||
### Required Environment Variables
|
||||
### Browserbase cloud mode
|
||||
|
||||
To use Browserbase-managed cloud browsers, add:
|
||||
|
||||
```bash
|
||||
# Add to ~/.hermes/.env
|
||||
BROWSERBASE_API_KEY=your-api-key-here
|
||||
BROWSERBASE_API_KEY=***
|
||||
BROWSERBASE_PROJECT_ID=your-project-id-here
|
||||
```
|
||||
|
||||
Get your credentials at [browserbase.com](https://browserbase.com).
|
||||
|
||||
### Local browser mode
|
||||
|
||||
If you do **not** set Browserbase credentials, Hermes can still use the browser tools through a local Chromium install driven by `agent-browser`.
|
||||
|
||||
### Optional Environment Variables
|
||||
|
||||
```bash
|
||||
|
|
|
|||
|
|
@ -298,7 +298,7 @@ hermes honcho peer --user NAME # Set user peer name
|
|||
hermes honcho peer --ai NAME # Set AI peer name
|
||||
hermes honcho peer --reasoning LEVEL # Set dialectic reasoning level
|
||||
hermes honcho mode # Show current memory mode
|
||||
hermes honcho mode [hybrid|honcho] # Set memory mode
|
||||
hermes honcho mode [hybrid|honcho|local] # Set memory mode
|
||||
hermes honcho tokens # Show token budget settings
|
||||
hermes honcho tokens --context N # Set context token cap
|
||||
hermes honcho tokens --dialectic N # Set dialectic char cap
|
||||
|
|
|
|||
|
|
@ -161,6 +161,8 @@ Tools appear alongside built-in tools — the agent calls them like any other to
|
|||
|
||||
:::info
|
||||
In addition to the server's own tools, each MCP server also gets 4 utility tools auto-registered: `list_resources`, `read_resource`, `list_prompts`, and `get_prompt`. These allow the agent to discover and use MCP resources and prompts exposed by the server.
|
||||
|
||||
Each configured server also creates a **runtime toolset** named `mcp-<server>`. This means you can filter or reason about MCP servers at the toolset level in the same way you do with built-in toolsets.
|
||||
:::
|
||||
|
||||
### Reconnection
|
||||
|
|
|
|||
|
|
@ -216,13 +216,17 @@ The system prompt is assembled in layers (from `agent/prompt_builder.py` and `ru
|
|||
**SOUL.md vs agent.system_prompt**: SOUL.md is part of the "Project Context" section and coexists with the default identity. The `agent.system_prompt` (set via `/personality` or config) is an ephemeral overlay. Both can be active simultaneously — SOUL.md for tone/personality, system_prompt for additional instructions.
|
||||
:::
|
||||
|
||||
## Display Personality (CLI Banner)
|
||||
## CLI Appearance vs Conversational Personality
|
||||
|
||||
The `display.personality` config option controls the CLI's **visual** personality (banner art, spinner messages), independent of the agent's conversational personality:
|
||||
Conversational personality and CLI appearance are separate:
|
||||
|
||||
- `agent.system_prompt`, `/personality`, and `SOUL.md` affect how Hermes **speaks**.
|
||||
- `display.skin` and `/skin` affect how Hermes **looks in the terminal**.
|
||||
|
||||
```yaml
|
||||
display:
|
||||
personality: kawaii # Affects CLI banner and spinner art
|
||||
skin: default
|
||||
# personality: kawaii # legacy cosmetic setting still shown in some summaries
|
||||
```
|
||||
|
||||
This is purely cosmetic and doesn't affect the agent's responses — only the ASCII art and loading messages shown in the terminal.
|
||||
For the full theming system — built-in skins, custom YAML skins, spinner branding, and `/skin` — see [Skins & Themes](./skins.md).
|
||||
|
|
|
|||
|
|
@ -10,6 +10,11 @@ Skills are on-demand knowledge documents the agent can load when needed. They fo
|
|||
|
||||
All skills live in **`~/.hermes/skills/`** — a single directory that serves as the source of truth. On fresh install, bundled skills are copied from the repo. Hub-installed and agent-created skills also go here. The agent can modify or delete any skill.
|
||||
|
||||
See also:
|
||||
|
||||
- [Bundled Skills Catalog](/docs/reference/skills-catalog)
|
||||
- [Official Optional Skills Catalog](/docs/reference/optional-skills-catalog)
|
||||
|
||||
## Using Skills
|
||||
|
||||
Every installed skill is automatically available as a slash command:
|
||||
|
|
@ -139,6 +144,7 @@ When a missing value is encountered, Hermes asks for it securely only when the s
|
|||
│ │ ├── SKILL.md # Main instructions (required)
|
||||
│ │ ├── references/ # Additional docs
|
||||
│ │ ├── templates/ # Output formats
|
||||
│ │ ├── scripts/ # Helper scripts callable from the skill
|
||||
│ │ └── assets/ # Supplementary files
|
||||
│ └── vllm/
|
||||
│ └── SKILL.md
|
||||
|
|
@ -199,6 +205,8 @@ hermes skills tap add myorg/skills-repo # Add a custom source
|
|||
|
||||
All hub-installed skills go through a **security scanner** that checks for data exfiltration, prompt injection, destructive commands, and other threats.
|
||||
|
||||
Official optional skills use identifiers like `official/security/1password` and `official/migration/openclaw-migration`.
|
||||
|
||||
### Trust Levels
|
||||
|
||||
| Level | Source | Policy |
|
||||
|
|
|
|||
81
website/docs/user-guide/features/skins.md
Normal file
81
website/docs/user-guide/features/skins.md
Normal file
|
|
@ -0,0 +1,81 @@
|
|||
---
|
||||
sidebar_position: 10
|
||||
title: "Skins & Themes"
|
||||
description: "Customize the Hermes CLI with built-in and user-defined skins"
|
||||
---
|
||||
|
||||
# Skins & Themes
|
||||
|
||||
Skins control the **visual presentation** of the Hermes CLI: banner colors, spinner faces and verbs, response-box labels, branding text, and the tool activity prefix.
|
||||
|
||||
Conversational style and visual style are separate concepts:
|
||||
|
||||
- **Personality** changes the agent's tone and wording.
|
||||
- **Skin** changes the CLI's appearance.
|
||||
|
||||
## Change skins
|
||||
|
||||
```bash
|
||||
/skin # show the current skin and list available skins
|
||||
/skin ares # switch to a built-in skin
|
||||
/skin mytheme # switch to a custom skin from ~/.hermes/skins/mytheme.yaml
|
||||
```
|
||||
|
||||
Or set the default skin in `~/.hermes/config.yaml`:
|
||||
|
||||
```yaml
|
||||
display:
|
||||
skin: default
|
||||
```
|
||||
|
||||
## Built-in skins
|
||||
|
||||
| Skin | Description | Agent branding |
|
||||
|------|-------------|----------------|
|
||||
| `default` | Classic Hermes — gold and kawaii | `Hermes Agent` |
|
||||
| `ares` | War-god theme — crimson and bronze | `Ares Agent` |
|
||||
| `mono` | Monochrome — clean grayscale | `Hermes Agent` |
|
||||
| `slate` | Cool blue — developer-focused | `Hermes Agent` |
|
||||
| `poseidon` | Ocean-god theme — deep blue and seafoam | `Poseidon Agent` |
|
||||
| `sisyphus` | Sisyphean theme — austere grayscale with persistence | `Sisyphus Agent` |
|
||||
| `charizard` | Volcanic theme — burnt orange and ember | `Charizard Agent` |
|
||||
|
||||
## What a skin can customize
|
||||
|
||||
| Area | Keys |
|
||||
|------|------|
|
||||
| Banner + response colors | `colors.banner_*`, `colors.response_border` |
|
||||
| Spinner animation | `spinner.waiting_faces`, `spinner.thinking_faces`, `spinner.thinking_verbs`, `spinner.wings` |
|
||||
| Branding text | `branding.agent_name`, `branding.welcome`, `branding.response_label`, `branding.prompt_symbol` |
|
||||
| Tool activity prefix | `tool_prefix` |
|
||||
|
||||
## Custom skins
|
||||
|
||||
Create YAML files under `~/.hermes/skins/`. User skins inherit missing values from the built-in `default` skin.
|
||||
|
||||
```yaml
|
||||
name: cyberpunk
|
||||
description: Neon terminal theme
|
||||
|
||||
colors:
|
||||
banner_border: "#FF00FF"
|
||||
banner_title: "#00FFFF"
|
||||
banner_accent: "#FF1493"
|
||||
|
||||
spinner:
|
||||
thinking_verbs: ["jacking in", "decrypting", "uploading"]
|
||||
wings:
|
||||
- ["⟨⚡", "⚡⟩"]
|
||||
|
||||
branding:
|
||||
agent_name: "Cyber Agent"
|
||||
response_label: " ⚡ Cyber "
|
||||
|
||||
tool_prefix: "▏"
|
||||
```
|
||||
|
||||
## Operational notes
|
||||
|
||||
- Built-in skins load from `hermes_cli/skin_engine.py`.
|
||||
- Unknown skins automatically fall back to `default`.
|
||||
- `/skin` updates the active CLI theme immediately for the current session.
|
||||
|
|
@ -10,25 +10,22 @@ Tools are functions that extend the agent's capabilities. They're organized into
|
|||
|
||||
## Available Tools
|
||||
|
||||
| Category | Tools | Description |
|
||||
|----------|-------|-------------|
|
||||
| **Web** | `web_search`, `web_extract` | Search the web, extract page content |
|
||||
| **Terminal** | `terminal`, `process` | Execute commands (local/docker/singularity/modal/daytona/ssh backends), manage background processes |
|
||||
| **File** | `read_file`, `write_file`, `patch`, `search_files` | Read, write, edit, and search files |
|
||||
| **Browser** | `browser_navigate`, `browser_click`, `browser_type`, `browser_console`, etc. | Full browser automation via Browserbase |
|
||||
| **Vision** | `vision_analyze` | Image analysis via multimodal models |
|
||||
| **Image Gen** | `image_generate` | Generate images (FLUX via FAL) |
|
||||
| **TTS** | `text_to_speech` | Text-to-speech (Edge TTS / ElevenLabs / OpenAI) |
|
||||
| **Reasoning** | `mixture_of_agents` | Multi-model reasoning |
|
||||
| **Skills** | `skills_list`, `skill_view`, `skill_manage` | Find, view, create, and manage skills |
|
||||
| **Todo** | `todo` | Read/write task list for multi-step planning |
|
||||
| **Memory** | `memory` | Persistent notes + user profile across sessions |
|
||||
| **Session Search** | `session_search` | Search + summarize past conversations (FTS5) |
|
||||
| **Cronjob** | `schedule_cronjob`, `list_cronjobs`, `remove_cronjob` | Scheduled task management |
|
||||
| **Code Execution** | `execute_code` | Run Python scripts that call tools via RPC sandbox |
|
||||
| **Delegation** | `delegate_task` | Spawn subagents with isolated context |
|
||||
| **Clarify** | `clarify` | Ask the user multiple-choice or open-ended questions |
|
||||
| **MCP** | Auto-discovered | External tools from MCP servers |
|
||||
Hermes ships with a broad built-in tool registry covering web search, browser automation, terminal execution, file editing, memory, delegation, RL training, messaging delivery, Home Assistant, Honcho memory, and more.
|
||||
|
||||
High-level categories:
|
||||
|
||||
| Category | Examples | Description |
|
||||
|----------|----------|-------------|
|
||||
| **Web** | `web_search`, `web_extract` | Search the web and extract page content. |
|
||||
| **Terminal & Files** | `terminal`, `process`, `read_file`, `patch` | Execute commands and manipulate files. |
|
||||
| **Browser** | `browser_navigate`, `browser_snapshot`, `browser_vision` | Interactive browser automation with text and vision support. |
|
||||
| **Media** | `vision_analyze`, `image_generate`, `text_to_speech` | Multimodal analysis and generation. |
|
||||
| **Agent orchestration** | `todo`, `clarify`, `execute_code`, `delegate_task` | Planning, clarification, code execution, and subagent delegation. |
|
||||
| **Memory & recall** | `memory`, `session_search`, `honcho_*` | Persistent memory, session search, and Honcho cross-session context. |
|
||||
| **Automation & delivery** | `schedule_cronjob`, `send_message` | Scheduled tasks and outbound messaging delivery. |
|
||||
| **Integrations** | `ha_*`, MCP server tools, `rl_*` | Home Assistant, MCP, RL training, and other integrations. |
|
||||
|
||||
For the authoritative code-derived registry, see [Built-in Tools Reference](/docs/reference/tools-reference) and [Toolsets Reference](/docs/reference/toolsets-reference).
|
||||
|
||||
## Using Toolsets
|
||||
|
||||
|
|
@ -43,7 +40,9 @@ hermes tools
|
|||
hermes tools
|
||||
```
|
||||
|
||||
**Available toolsets:** `web`, `terminal`, `file`, `browser`, `vision`, `image_gen`, `moa`, `skills`, `tts`, `todo`, `memory`, `session_search`, `cronjob`, `code_execution`, `delegation`, `clarify`, and more.
|
||||
Common toolsets include `web`, `terminal`, `file`, `browser`, `vision`, `image_gen`, `moa`, `skills`, `tts`, `todo`, `memory`, `session_search`, `cronjob`, `code_execution`, `delegation`, `clarify`, `honcho`, `homeassistant`, and `rl`.
|
||||
|
||||
See [Toolsets Reference](/docs/reference/toolsets-reference) for the full set, including platform presets such as `hermes-cli`, `hermes-telegram`, and dynamic MCP toolsets like `mcp-<server>`.
|
||||
|
||||
## Terminal Backends
|
||||
|
||||
|
|
@ -56,6 +55,7 @@ The terminal tool can execute commands in different environments:
|
|||
| `ssh` | Remote server | Sandboxing, keep agent away from its own code |
|
||||
| `singularity` | HPC containers | Cluster computing, rootless |
|
||||
| `modal` | Cloud execution | Serverless, scale |
|
||||
| `daytona` | Cloud sandbox workspace | Persistent remote dev environments |
|
||||
|
||||
### Configuration
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue