nanobot
Описание
"🐈 nanobot: The Ultra-Lightweight OpenClaw" fork https://github.com/HKUDS/nanobot
Языки
- Python87,3%
- Shell5,5%
- PowerShell4,4%
- TypeScript2,1%
- Dockerfile0,4%
- JavaScript0,3%
🐈 nanobot is an ultra-lightweight personal AI assistant inspired by OpenClaw
⚡️ Delivers core agent functionality in just ~4,000 lines of code — 99% smaller than Clawdbot's 430k+ lines.
📏 Real-time line count: 3,510 lines (run to verify anytime)
📢 News
- 2026-02-10 🎉 Released v0.1.3.post6 with improvements! Check the updates notes and our roadmap.
- 2026-02-09 💬 Added Slack, Email, and QQ support — nanobot now supports multiple chat platforms!
- 2026-02-08 🔧 Refactored Providers—adding a new LLM provider now takes just 2 simple steps! Check here.
- 2026-02-07 🚀 Released v0.1.3.post5 with Qwen support & several key improvements! Check here for details.
- 2026-02-06 ✨ Added Moonshot/Kimi provider, Discord integration, and enhanced security hardening!
- 2026-02-05 ✨ Added Feishu channel, DeepSeek provider, and enhanced scheduled tasks support!
- 2026-02-04 🚀 Released v0.1.3.post4 with multi-provider & Docker support! Check here for details.
- 2026-02-03 ⚡ Integrated vLLM for local LLM support and improved natural language task scheduling!
- 2026-02-02 🎉 nanobot officially launched! Welcome to try 🐈 nanobot!
Key Features of nanobot:
🪶 Ultra-Lightweight: Just ~4,000 lines of core agent code — 99% smaller than Clawdbot.
🔬 Research-Ready: Clean, readable code that's easy to understand, modify, and extend for research.
⚡️ Lightning Fast: Minimal footprint means faster startup, lower resource usage, and quicker iterations.
💎 Easy-to-Use: One-click to deploy and you're ready to go.
🏗️ Architecture
✨ Features
📈 24/7 Real-Time Market Analysis | 🚀 Full-Stack Software Engineer | 📅 Smart Daily Routine Manager | 📚 Personal Knowledge Assistant |
|---|---|---|---|
|
|
|
|
| Discovery • Insights • Trends | Develop • Deploy • Scale | Schedule • Automate • Organize | Learn • Memory • Reasoning |
📦 Install
Install from source (latest features, recommended for development)
Install with uv (stable, fast)
Install from PyPI (stable)
🚀 Quick Start
Tip
Set your API key in
. Get API keys: OpenRouter (Global) · Brave Search (optional, for web search)~/.nanobot/config.json
1. Initialize
2. Configure ()
For OpenRouter - recommended for global users:
3. Chat
That's it! You have a working AI assistant in 2 minutes.
Update Without Losing Memory
Your agent's memory and local configuration are safely preserved during updates.
How it works:
- Memory is stored in
(automatically ignored by git)~/.nanobot/workspace/ - Your configuration in
is local and won't be overwritten~/.nanobot/config.json - Daily notes and long-term memory survive all updates
To update safely:
✅ Your memory, session history, and custom configurations remain intact.
Note
- UPDATE.md — One-command update (recommended)
- UPDATE_SAFELY.md — Backup and recovery instructions
- RULES_MANAGEMENT.md — How to update agent instructions and rules
- RULES_REFERENCE.md — Quick reference for managing rules
Local Models (vLLM)
Run nanobot with your own local models using vLLM or any OpenAI-compatible server.
1. Start your vLLM server
2. Configure ()
3. Chat
Tip
The
can be any non-empty string for local servers that don't require authentication.apiKey
💬 Chat Apps
Talk to your nanobot through Telegram, Discord, WhatsApp, Feishu, Mochat, DingTalk, Slack, Email, or QQ — anytime, anywhere.
| Channel | Setup |
|---|---|
| Telegram | Easy (just a token) |
| Discord | Easy (bot token + intents) |
| Medium (scan QR) | |
| Feishu | Medium (app credentials) |
| Mochat | Medium (claw token + websocket) |
| DingTalk | Medium (app credentials) |
| Slack | Medium (bot + app tokens) |
| Medium (IMAP/SMTP credentials) | |
| Easy (app credentials) |
Telegram (Recommended)
1. Create a bot
- Open Telegram, search @BotFather
- Send
, follow prompts/newbot - Copy the token
2. Configure
You can find your User ID in Telegram settings. It is shown as
. Copy this value without the@yourUserIdsymbol and paste it into the config file.@
3. Run
Mochat (Claw IM)
Uses Socket.IO WebSocket by default, with HTTP polling fallback.
1. Ask nanobot to set up Mochat for you
Simply send this message to nanobot (replace with your real email):
Read https://raw.githubusercontent.com/HKUDS/MoChat/refs/heads/main/skills/nanobot/skill.md and register on MoChat. My Email account is xxx@xxx Bind me as your owner and DM me on MoChat.
nanobot will automatically register, configure , and connect to Mochat.
2. Restart gateway
That's it — nanobot handles the rest!
Manual configuration (advanced)
If you prefer to configure manually, add the following to :
Keep
private. It should only be sent inclaw_tokenheader to your Mochat API endpoint.X-Claw-Token
Discord
1. Create a bot
- Go to https://discord.com/developers/applications
- Create an application → Bot → Add Bot
- Copy the bot token
2. Enable intents
- In the Bot settings, enable MESSAGE CONTENT INTENT
- (Optional) Enable SERVER MEMBERS INTENT if you plan to use allow lists based on member data
3. Get your User ID
- Discord Settings → Advanced → enable Developer Mode
- Right-click your avatar → Copy User ID
4. Configure
5. Invite the bot
- OAuth2 → URL Generator
- Scopes: bot
- Bot Permissions:
,Send MessagesRead Message History - Open the generated invite URL and add the bot to your server
6. Run
Requires Node.js ≥18.
1. Link device
2. Configure
3. Run (two terminals)
Feishu (飞书)
Uses WebSocket long connection — no public IP required.
1. Create a Feishu bot
- Visit Feishu Open Platform
- Create a new app → Enable Bot capability
- Permissions: Add
(send messages)im:message - Events: Add
(receive messages)im.message.receive_v1- Select Long Connection mode (requires running nanobot first to establish connection)
- Get App ID and App Secret from "Credentials & Basic Info"
- Publish the app
2. Configure
andencryptKeyare optional for Long Connection mode.verificationToken: Leave empty to allow all users, or addallowFromto restrict access.["ou_xxx"]
3. Run
Tip
Feishu uses WebSocket to receive messages — no webhook or public IP needed!
QQ (QQ单聊)
Uses botpy SDK with WebSocket — no public IP required. Currently supports private messages only.
1. Register & create bot
- Visit QQ Open Platform → Register as a developer (personal or enterprise)
- Create a new bot application
- Go to 开发设置 (Developer Settings) → copy AppID and AppSecret
2. Set up sandbox for testing
- In the bot management console, find 沙箱配置 (Sandbox Config)
- Under 在消息列表配置, click 添加成员 and add your own QQ number
- Once added, scan the bot's QR code with mobile QQ → open the bot profile → tap "发消息" to start chatting
3. Configure
: Leave empty for public access, or add user openids to restrict. You can find openids in the nanobot logs when a user messages the bot.allowFrom- For production: submit a review in the bot console and publish. See QQ Bot Docs for the full publishing flow.
4. Run
Now send a message to the bot from QQ — it should respond!
DingTalk (钉钉)
Uses Stream Mode — no public IP required.
1. Create a DingTalk bot
- Visit DingTalk Open Platform
- Create a new app -> Add Robot capability
- Configuration:
- Toggle Stream Mode ON
- Permissions: Add necessary permissions for sending messages
- Get AppKey (Client ID) and AppSecret (Client Secret) from "Credentials"
- Publish the app
2. Configure
: Leave empty to allow all users, or addallowFromto restrict access.["staffId"]
3. Run
Slack
Uses Socket Mode — no public URL required.
1. Create a Slack app
- Go to Slack API → Create New App → "From scratch"
- Pick a name and select your workspace
2. Configure the app
- Socket Mode: Toggle ON → Generate an App-Level Token with
scope → copy it (connections:write)xapp-... - OAuth & Permissions: Add bot scopes:
,chat:write,reactions:writeapp_mentions:read - Event Subscriptions: Toggle ON → Subscribe to bot events:
,message.im,message.channels→ Save Changesapp_mention - App Home: Scroll to Show Tabs → Enable Messages Tab → Check "Allow users to send Slash commands and messages from the messages tab"
- Install App: Click Install to Workspace → Authorize → copy the Bot Token (
)xoxb-...
3. Configure nanobot
4. Run
DM the bot directly or @mention it in a channel — it should respond!
Tip
:groupPolicy(default — respond only when @mentioned),"mention"(respond to all channel messages), or"open"(restrict to specific channels)."allowlist"- DM policy defaults to open. Set
to disable DMs."dm": {"enabled": false}
Give nanobot its own email account. It polls IMAP for incoming mail and replies via SMTP — like a personal email assistant.
1. Get credentials (Gmail example)
- Create a dedicated Gmail account for your bot (e.g.
)my-nanobot@gmail.com - Enable 2-Step Verification → Create an App Password
- Use this app password for both IMAP and SMTP
2. Configure
must beconsentGrantedto allow mailbox access. This is a safety gate — settrueto fully disable.false: Leave empty to accept emails from anyone, or restrict to specific senders.allowFromandsmtpUseTlsdefault tosmtpUseSsl/truerespectively, which is correct for Gmail (port 587 + STARTTLS). No need to set them explicitly.false- Set
if you only want to read/analyze emails without sending automatic replies."autoReplyEnabled": false
3. Run
⚙️ Configuration
Config file:
Providers
Tip
- Groq provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed.
- Zhipu Coding Plan: If you're on Zhipu's coding plan, set
in your zhipu provider config."apiBase": "https://open.bigmodel.cn/api/coding/paas/v4"- MiniMax (Mainland China): If your API key is from MiniMax's mainland China platform (minimaxi.com), set
in your minimax provider config."apiBase": "https://api.minimaxi.com/v1"
| Provider | Purpose | Get API Key |
|---|---|---|
| LLM (recommended, access to all models) | openrouter.ai |
| LLM (Claude direct) | console.anthropic.com |
| LLM (GPT direct) | platform.openai.com |
| LLM (DeepSeek direct) | platform.deepseek.com |
| LLM + Voice transcription (Whisper) | console.groq.com |
| LLM (Gemini direct) | aistudio.google.com |
| LLM (MiniMax direct) | platform.minimax.io |
| LLM (API gateway, access to all models) | aihubmix.com |
| LLM (Qwen) | dashscope.console.aliyun.com |
| LLM (Moonshot/Kimi) | platform.moonshot.cn |
| LLM (Zhipu GLM) | open.bigmodel.cn |
| LLM (local, any OpenAI-compatible server) | — |
Adding a New Provider (Developer Guide)
nanobot uses a Provider Registry () as the single source of truth.
Adding a new provider only takes 2 steps — no if-elif chains to touch.
Step 1. Add a entry to in :
Step 2. Add a field to in :
That's it! Environment variables, model prefixing, config matching, and display will all work automatically.
Common options:
| Field | Description | Example |
|---|---|---|
| Auto-prefix model names for LiteLLM | → |
| Don't prefix if model already starts with these | |
| Additional env vars to set | |
| Per-model parameter overrides | |
| Can route any model (like OpenRouter) | |
| Detect gateway by API key prefix | |
| Detect gateway by API base URL | |
| Strip existing prefix before re-prefixing | (for AiHubMix) |
Security
For production deployments, set
in your config to sandbox the agent."restrictToWorkspace": true
| Option | Default | Description |
|---|---|---|
| | When , restricts all agent tools (shell, file read/write/edit, list) to the workspace directory. Prevents path traversal and out-of-scope access. |
| (allow all) | Whitelist of user IDs. Empty = allow everyone; non-empty = only listed users can interact. |
CLI Reference
| Command | Description |
|---|---|
| Initialize config & workspace |
| Chat with the agent |
| Interactive chat mode |
| Show plain-text replies |
| Show runtime logs during chat |
| Start the gateway |
| Show status |
| Link WhatsApp (scan QR) |
| Show channel status |
Interactive mode exits: , , , , , or .
Scheduled Tasks (Cron)
🐳 Docker
Tip
The
flag mounts your local config directory into the container, so your config and workspace persist across container restarts.-v ~/.nanobot:/root/.nanobot
Build and run nanobot in a container:
📁 Project Structure
nanobot/
├── agent/ # 🧠 Core agent logic
│ ├── loop.py # Agent loop (LLM ↔ tool execution)
│ ├── context.py # Prompt builder
│ ├── memory.py # Persistent memory
│ ├── skills.py # Skills loader
│ ├── subagent.py # Background task execution
│ └── tools/ # Built-in tools (incl. spawn)
├── skills/ # 🎯 Bundled skills (github, weather, tmux...)
├── channels/ # 📱 Chat channel integrations
├── bus/ # 🚌 Message routing
├── cron/ # ⏰ Scheduled tasks
├── heartbeat/ # 💓 Proactive wake-up
├── providers/ # 🤖 LLM providers (OpenRouter, etc.)
├── session/ # 💬 Conversation sessions
├── config/ # ⚙️ Configuration
├── cli/ # 🖥️ Commands
└── workspace/
└── defaults/ # 📋 Default agent rules & instructions
Your custom rules go in — see RULES_MANAGEMENT.md for details.
🤝 Contribute & Roadmap
PRs welcome! The codebase is intentionally small and readable. 🤗
Roadmap — Pick an item and open a PR!
- Voice Transcription — Support for Groq Whisper (Issue #13)
- Multi-modal — See and hear (images, voice, video)
- Long-term memory — Never forget important context
- Better reasoning — Multi-step planning and reflection
- More integrations — Calendar and more
- Self-improvement — Learn from feedback and mistakes
Contributors
⭐ Star History
Thanks for visiting ✨ nanobot!
nanobot is for educational, research, and technical exchange purposes only



