π nanobot is an open-source and ultra-lightweight AI agent in the spirit of OpenClaw, Claude Code, and Codex. It keeps the core agent loop small and readable while still supporting chat channels, memory, MCP and practical deployment paths, so you can go from local setup to a long-running personal agent with minimal overhead.
- 2026-04-14 π Released v0.1.5.post1 β Dream skill discovery, mid-turn follow-up injection, WebSocket channel, and deeper channel integrations. Please see release notes for details.
- 2026-04-13 π‘οΈ Agent turn hardened β user messages persisted early, auto-compact skips active tasks.
- 2026-04-12 π Lark global domain support, Dream learns discovered skills, shell sandbox tightened.
- 2026-04-11 β‘ Context compact shrinks sessions on the fly; Kagi web search; QQ & WeCom full media.
- 2026-04-10 π Notebook editing tool, multiple MCP servers, Feishu streaming & done-emoji.
- 2026-04-09 π WebSocket channel, unified cross-channel session,
disabled_skillsconfig. - 2026-04-08 π€ API file uploads, OpenAI reasoning auto-routing with Responses fallback.
- 2026-04-07 π§ Anthropic adaptive thinking, MCP resources & prompts exposed as tools.
- 2026-04-06 π°οΈ Langfuse observability, unified Whisper transcription, email attachments.
- 2026-04-05 π Released v0.1.5 β sturdier long-running tasks, Dream two-stage memory, production-ready sandboxing and programming Agent SDK. Please see release notes for details.
Earlier news
- 2026-04-04 π Jinja2 response templates, Dream memory hardened, smarter retry handling.
- 2026-04-03 π§ Xiaomi MiMo provider, chain-of-thought reasoning visible, Telegram UX polish.
- 2026-04-02 π§± Long-running tasks run more reliably β core runtime hardening.
- 2026-04-01 π GitHub Copilot auth restored; stricter workspace paths; OpenRouter Claude caching fix.
- 2026-03-31 π°οΈ WeChat multimodal alignment, Discord/Matrix polish, Python SDK facade, MCP and tool fixes.
- 2026-03-30 π§© OpenAI-compatible API tightened; composable agent lifecycle hooks.
- 2026-03-29 π¬ WeChat voice, typing, QR/media resilience; fixed-session OpenAI-compatible API.
- 2026-03-28 π Provider docs refresh; skill template wording fix.
- 2026-03-27 π Released v0.1.4.post6 β architecture decoupling, litellm removal, end-to-end streaming, WeChat channel, and a security fix. Please see release notes for details.
- 2026-03-26 ποΈ Agent runner extracted and lifecycle hooks unified; stream delta coalescing at boundaries.
- 2026-03-25 π StepFun provider, configurable timezone, Gemini thought signatures.
- 2026-03-24 π§ WeChat compatibility, Feishu CardKit streaming, test suite restructured.
- 2026-03-23 π§ Command routing refactored for plugins, WhatsApp/WeChat media, unified channel login CLI.
- 2026-03-22 β‘ End-to-end streaming, WeChat channel, Anthropic cache optimization,
/statuscommand. - 2026-03-21 π Replace
litellmwith nativeopenai+anthropicSDKs. Please see commit. - 2026-03-20 π§ Interactive setup wizard β pick your provider, model autocomplete, and you're good to go.
- 2026-03-19 π¬ Telegram gets more resilient under load; Feishu now renders code blocks properly.
- 2026-03-18 π· Telegram can now send media via URL. Cron schedules show human-readable details.
- 2026-03-17 β¨ Feishu formatting glow-up, Slack reacts when done, custom endpoints support extra headers, and image handling is more reliable.
- 2026-03-16 π Released v0.1.4.post5 β a refinement-focused release with stronger reliability and channel support, and a more dependable day-to-day experience. Please see release notes for details.
- 2026-03-15 π§© DingTalk rich media, smarter built-in skills, and cleaner model compatibility.
- 2026-03-14 π¬ Channel plugins, Feishu replies, and steadier MCP, QQ, and media handling.
- 2026-03-13 π Multi-provider web search, LangSmith, and broader reliability improvements.
- 2026-03-12 π VolcEngine support, Telegram reply context,
/restart, and sturdier memory. - 2026-03-11 π WeCom, Ollama, cleaner discovery, and safer tool behavior.
- 2026-03-10 π§ Token-based memory, shared retries, and cleaner gateway and Telegram behavior.
- 2026-03-09 π¬ Slack thread polish and better Feishu audio compatibility.
- 2026-03-08 π Released v0.1.4.post4 β a reliability-packed release with safer defaults, better multi-instance support, sturdier MCP, and major channel and provider improvements. Please see release notes for details.
- 2026-03-07 π Azure OpenAI provider, WhatsApp media, QQ group chats, and more Telegram/Feishu polish.
- 2026-03-06 πͺ Lighter providers, smarter media handling, and sturdier memory and CLI compatibility.
- 2026-03-05 β‘οΈ Telegram draft streaming, MCP SSE support, and broader channel reliability fixes.
- 2026-03-04 π οΈ Dependency cleanup, safer file reads, and another round of test and Cron fixes.
- 2026-03-03 π§ Cleaner user-message merging, safer multimodal saves, and stronger Cron guards.
- 2026-03-02 π‘οΈ Safer default access control, sturdier Cron reloads, and cleaner Matrix media handling.
- 2026-03-01 π Web proxy support, smarter Cron reminders, and Feishu rich-text parsing improvements.
- 2026-02-28 π Released v0.1.4.post3 β cleaner context, hardened session history, and smarter agent. Please see release notes for details.
- 2026-02-27 π§ Experimental thinking mode support, DingTalk media messages, Feishu and QQ channel fixes.
- 2026-02-26 π‘οΈ Session poisoning fix, WhatsApp dedup, Windows path guard, Mistral compatibility.
- 2026-02-25 π§Ή New Matrix channel, cleaner session context, auto workspace template sync.
- 2026-02-24 π Released v0.1.4.post2 β a reliability-focused release with a redesigned heartbeat, prompt cache optimization, and hardened provider & channel stability. See release notes for details.
- 2026-02-23 π§ Virtual tool-call heartbeat, prompt cache optimization, Slack mrkdwn fixes.
- 2026-02-22 π‘οΈ Slack thread isolation, Discord typing fix, agent reliability improvements.
- 2026-02-21 π Released v0.1.4.post1 β new providers, media support across channels, and major stability improvements. See release notes for details.
- 2026-02-20 π¦ Feishu now receives multimodal files from users. More reliable memory under the hood.
- 2026-02-19 β¨ Slack now sends files, Discord splits long messages, and subagents work in CLI mode.
- 2026-02-18 β‘οΈ nanobot now supports VolcEngine, MCP custom auth headers, and Anthropic prompt caching.
- 2026-02-17 π Released v0.1.4 β MCP support, progress streaming, new providers, and multiple channel improvements. Please see release notes for details.
- 2026-02-16 π¦ nanobot now integrates a ClawHub skill β search and install public agent skills.
- 2026-02-15 π nanobot now supports OpenAI Codex provider with OAuth login support.
- 2026-02-14 π nanobot now supports MCP! See MCP section for details.
- 2026-02-13 π Released v0.1.3.post7 β includes security hardening and multiple improvements. Please upgrade to the latest version to address security issues. See release notes for more details.
- 2026-02-12 π§ Redesigned memory system β Less code, more reliable. Join the discussion about it!
- 2026-02-11 β¨ Enhanced CLI experience and added MiniMax support!
- 2026-02-10 π Released v0.1.3.post6 with improvements! Check the updates notes and our roadmap.
- 2026-02-09 π¬ Added Slack, Email, and QQ support β nanobot now supports multiple chat platforms!
- 2026-02-08 π§ Refactored Providersβadding a new LLM provider now takes just 2 simple steps! Check here.
- 2026-02-07 π Released v0.1.3.post5 with Qwen support & several key improvements! Check here for details.
- 2026-02-06 β¨ Added Moonshot/Kimi provider, Discord integration, and enhanced security hardening!
- 2026-02-05 β¨ Added Feishu channel, DeepSeek provider, and enhanced scheduled tasks support!
- 2026-02-04 π Released v0.1.3.post4 with multi-provider & Docker support! Check here for details.
- 2026-02-03 β‘ Integrated vLLM for local LLM support and improved natural language task scheduling!
- 2026-02-02 π nanobot officially launched! Welcome to try π nanobot!
- Ultra-lightweight: stable long-running agent behavior with a small, readable core.
- Research-ready: the codebase is intentionally simple enough to study, modify, and extend.
- Practical: chat channels, API, memory, MCP, and deployment paths are already built in.
- Hackable: you can start fast, then go deeper through repo docs instead of a monolithic landing page.
Important
If you want the newest features and experiments, install from source.
If you want the most stable day-to-day experience, install from PyPI or with uv.
Install from source
git clone https://github.com/HKUDS/nanobot.git
cd nanobot
pip install -e .Install with uv
uv tool install nanobot-aiInstall from PyPI
pip install nanobot-ai1. Initialize
nanobot onboard2. Configure (~/.nanobot/config.json)
Configure these two parts in your config (other options have defaults). Add or merge the following blocks into your existing config instead of replacing the whole file.
Set your API key (e.g. OpenRouter, recommended for global users):
{
"providers": {
"openrouter": {
"apiKey": "sk-or-v1-xxx"
}
}
}Set your model (optionally pin a provider β defaults to auto-detection):
{
"agents": {
"defaults": {
"provider": "openrouter",
"model": "anthropic/claude-opus-4-6"
}
}
}3. Chat
nanobot agent- Want different LLM providers, web search, MCP, security settings, or more config options? See Configuration
- Want to run nanobot in chat apps like Telegram, Discord, WeChat or Feishu? See Chat Apps
- Want Docker or Linux service deployment? See Deployment
Note
The WebUI development workflow currently requires a source checkout and is not yet shipped together with the official packaged release. See WebUI Document for full WebUI development docs and build steps.
1. Start the gateway
nanobot gateway2. Start the webui dev server
cd webui
bun install
bun run devπ nanobot stays lightweight by centering everything around a small agent loop: messages come in from chat apps, the LLM decides when tools are needed, and memory or skills are pulled in only as context instead of becoming a heavy orchestration layer. That keeps the core path readable and easy to extend, while still letting you add channels, tools, memory, and deployment options without turning the system into a monolith.
π 24/7 Real-Time Market Analysis |
π Full-Stack Software Engineer |
π Smart Daily Routine Manager |
π Personal Knowledge Assistant |
|---|---|---|---|
| Discovery β’ Insights β’ Trends | Develop β’ Deploy β’ Scale | Schedule β’ Automate β’ Organize | Learn β’ Memory β’ Reasoning |
Browse the repo docs for the latest features and GitHub development version, or visit nanobot.wiki for the stable release documentation.
- Talk to your nanobot with familiar chat apps: Chat Apps
- Configure providers, web search, MCP, and runtime behavior: Configuration
- Integrate nanobot with local tools and automations: OpenAI-Compatible API Β· Python SDK
- Run nanobot with Docker or as a Linux service: Deployment
PRs welcome! The codebase is intentionally small and readable. π€
| Branch | Purpose |
|---|---|
main |
Stable releases β bug fixes and minor improvements |
nightly |
Experimental features β new features and breaking changes |
Unsure which branch to target? See CONTRIBUTING.md for details.
Roadmap β Pick an item and open a PR!
- Multi-modal β See and hear (images, voice, video)
- Long-term memory β Never forget important context
- Better reasoning β Multi-step planning and reflection
- More integrations β Calendar and more
- Self-improvement β Learn from feedback and mistakes