mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-18 04:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

docs: update NovitaAI description to "90+ models, pay-per-use"

Browse source
This commit is contained in:
Alex-wuhu 2026-04-13 10:30:41 +08:00 • committed by kshitij
parent c76e879574
commit 1551ce46a4
6 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.env.example
View file

@ -17,7 +17,7 @@
# ============================================================================= # =============================================================================
# LLM PROVIDER (NovitaAI) # LLM PROVIDER (NovitaAI)
# ============================================================================= # =============================================================================
# NovitaAI — multi-model aggregator with pay-per-use pricing # NovitaAI — 90+ models, pay-per-use
# Get your key at: https://novita.ai/settings/key-management # Get your key at: https://novita.ai/settings/key-management
# NOVITA_API_KEY= # NOVITA_API_KEY=
# NOVITA_BASE_URL=https://api.novita.ai/openai/v1 # Override default base URL # NOVITA_BASE_URL=https://api.novita.ai/openai/v1 # Override default base URL

2
README.md
View file

@ -14,7 +14,7 @@
**The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM. **The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.
Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NovitaAI](https://novita.ai) (multi-model, pay-per-use), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in. Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NovitaAI](https://novita.ai) (90+ models, pay-per-use), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
<table> <table>
<tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr> <tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr>

2
agent/auxiliary_client.py
View file

@ -4436,7 +4436,7 @@ def extract_content_or_reasoning(response) -> str:
1. ``message.content`` — strip inline think/reasoning blocks, check for 1. ``message.content`` — strip inline think/reasoning blocks, check for
remaining non-whitespace text. remaining non-whitespace text.
2. ``message.reasoning`` / ``message.reasoning_content`` — direct 2. ``message.reasoning`` / ``message.reasoning_content`` — direct
structured reasoning fields (DeepSeek, Moonshot, Novita, etc.). structured reasoning fields (DeepSeek, Moonshot, NovitaAI, etc.).
3. ``message.reasoning_details`` — OpenRouter unified array format. 3. ``message.reasoning_details`` — OpenRouter unified array format.
Returns the best available text, or ``""`` if nothing found. Returns the best available text, or ``""`` if nothing found.

2
plugins/model-providers/novita/__init__.py
View file

@ -8,7 +8,7 @@ novita = ProviderProfile(
name="novita", name="novita",
aliases=("novita-ai", "novitaai"), aliases=("novita-ai", "novitaai"),
display_name="NovitaAI", display_name="NovitaAI",
description="NovitaAI — multi-model aggregator with pay-per-use pricing", description="NovitaAI — 90+ models, pay-per-use",
signup_url="https://novita.ai/settings/key-management", signup_url="https://novita.ai/settings/key-management",
env_vars=("NOVITA_API_KEY", "NOVITA_BASE_URL"), env_vars=("NOVITA_API_KEY", "NOVITA_BASE_URL"),
base_url="https://api.novita.ai/openai/v1", base_url="https://api.novita.ai/openai/v1",

4
website/docs/integrations/providers.md
View file

@ -20,7 +20,7 @@ You need at least one way to connect to an LLM. Use `hermes model` to switch pro
| **GitHub Copilot ACP** | `hermes model` (spawns local `copilot --acp --stdio`) | | **GitHub Copilot ACP** | `hermes model` (spawns local `copilot --acp --stdio`) |
| **Anthropic** | `hermes model` (Claude Max + extra usage credits via OAuth; also supports Anthropic API key or manual setup-token — see note below) | | **Anthropic** | `hermes model` (Claude Max + extra usage credits via OAuth; also supports Anthropic API key or manual setup-token — see note below) |
| **OpenRouter** | `OPENROUTER_API_KEY` in `~/.hermes/.env` | | **OpenRouter** | `OPENROUTER_API_KEY` in `~/.hermes/.env` |
| **NovitaAI** | `NOVITA_API_KEY` in `~/.hermes/.env` (provider: `novita`, multi-model aggregator) | | **NovitaAI** | `NOVITA_API_KEY` in `~/.hermes/.env` (provider: `novita`, 90+ models, pay-per-use) |
| **AI Gateway** | `AI_GATEWAY_API_KEY` in `~/.hermes/.env` (provider: `ai-gateway`) | | **AI Gateway** | `AI_GATEWAY_API_KEY` in `~/.hermes/.env` (provider: `ai-gateway`) |
| **z.ai / GLM** | `GLM_API_KEY` in `~/.hermes/.env` (provider: `zai`) | | **z.ai / GLM** | `GLM_API_KEY` in `~/.hermes/.env` (provider: `zai`) |
| **Kimi / Moonshot** | `KIMI_API_KEY` in `~/.hermes/.env` (provider: `kimi-coding`) | | **Kimi / Moonshot** | `KIMI_API_KEY` in `~/.hermes/.env` (provider: `kimi-coding`) |
@ -549,7 +549,7 @@ The base URL can be overridden with `HF_BASE_URL`.
### NovitaAI ### NovitaAI
[NovitaAI](https://novita.ai) is a multi-model aggregator with pay-per-use pricing. Access models from DeepSeek, Kimi, MiniMax, GLM, Qwen, and more through a unified OpenAI-compatible API. [NovitaAI](https://novita.ai) is a 90+ model aggregator with pay-per-use pricing. Access models from DeepSeek, Kimi, MiniMax, GLM, Qwen, and more through a unified OpenAI-compatible API.
```bash ```bash
# Use any available model # Use any available model

2
website/docs/reference/environment-variables.md
View file

@ -67,7 +67,7 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
| `DASHSCOPE_BASE_URL` | Custom DashScope base URL (default: `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`; use `https://dashscope.aliyuncs.com/compatible-mode/v1` for mainland-China region) | | `DASHSCOPE_BASE_URL` | Custom DashScope base URL (default: `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`; use `https://dashscope.aliyuncs.com/compatible-mode/v1` for mainland-China region) |
| `DEEPSEEK_API_KEY` | DeepSeek API key for direct DeepSeek access ([platform.deepseek.com](https://platform.deepseek.com/api_keys)) | | `DEEPSEEK_API_KEY` | DeepSeek API key for direct DeepSeek access ([platform.deepseek.com](https://platform.deepseek.com/api_keys)) |
| `DEEPSEEK_BASE_URL` | Custom DeepSeek API base URL | | `DEEPSEEK_BASE_URL` | Custom DeepSeek API base URL |
| `NOVITA_API_KEY` | NovitaAI API key — multi-model aggregator ([novita.ai/settings/key-management](https://novita.ai/settings/key-management)) | | `NOVITA_API_KEY` | NovitaAI API key — 90+ models, pay-per-use ([novita.ai/settings/key-management](https://novita.ai/settings/key-management)) |
| `NOVITA_BASE_URL` | Override NovitaAI base URL (default: `https://api.novita.ai/openai/v1`) | | `NOVITA_BASE_URL` | Override NovitaAI base URL (default: `https://api.novita.ai/openai/v1`) |
| `NVIDIA_API_KEY` | NVIDIA NIM API key — Nemotron and open models ([build.nvidia.com](https://build.nvidia.com)) | | `NVIDIA_API_KEY` | NVIDIA NIM API key — Nemotron and open models ([build.nvidia.com](https://build.nvidia.com)) |
| `NVIDIA_BASE_URL` | Override NVIDIA base URL (default: `https://integrate.api.nvidia.com/v1`; set to `http://localhost:8000/v1` for a local NIM endpoint) | | `NVIDIA_BASE_URL` | Override NVIDIA base URL (default: `https://integrate.api.nvidia.com/v1`; set to `http://localhost:8000/v1` for a local NIM endpoint) |