# HKUDS/nanobot

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

Repository: https://github.com/HKUDS/nanobot
Canonical: https://ross.abutalabs.com/products/nanobot
Homepage: https://nanobot.wiki
Language: Python
License: MIT
License Family: permissive
Topics: ai-agent, ai-agents, openclaw, agent-framework, chatbot, chatops, discord-bot, llm-agents, llms, local-llm, mcp, model-context-protocol, multi-agent, openai-compatible, personal-ai-assistant, python, self-hosted, telegram-bot-ai-assistant, webui, workflow-automation
Last push: 2026-08-26T14:59:45+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 95, longevity 15
- inputs: {"age_days": 213, "days_push": 7, "days_rel": 39, "gap_med": 7.0, "n_releases_24m": 19}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 47427, forks 8369 (observed 2026-08-28T04:12:11.206993+00:00)

## What it is
nanobot is an ultra-lightweight, self-hosted personal AI agent framework written in Python. It provides a WebUI, terminal, and chat-app interfaces with tools, long-term memory, MCP integrations, multi-agent delegation, scheduled automation, and an OpenAI-compatible API.

## Use cases
- run a self-hosted personal AI assistant with a web UI
- build a chatbot that works in Telegram or Discord
- connect my agent to tools via MCP servers
- automate scheduled tasks with an AI agent
- run multi-agent workflows with delegation
- expose an OpenAI-compatible API for my local agent
- give my assistant long-term memory across sessions

## When to choose
- you want a lightweight, readable agent core you can self-host
- you need WebUI, terminal, and chat-app access from one agent
- you want MCP tool integrations and multi-agent orchestration out of the box
- you prefer MIT-licensed Python code with predictable token budgets

## When to avoid
- you need a heavyweight enterprise agent platform with extensive vendor support
- you want a no-code hosted solution rather than running your own infrastructure
- you require non-Python runtimes or embedded deployment

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, chatbot, mcp, llm-inference, workflow-automation, web-framework, cli, chat-interface
- domain: large-language-models, chatbots, self-hosted, developer-tools
- platform: python, self-hosted, cli, cross-platform
- tags: personal-ai-assistant, multi-agent, openai-compatible, telegram-bot, discord-bot, webui, long-term-memory, model-routing, scheduled-automation, ai-agents, automation, web-server

## Member repositories
- HKUDS/nanobot (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.206993+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:21:01.623923+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/nanobot (fetched 2026-08-28T04:12:11.206993+00:00, sha b102ef134c2e)
  - homepage: https://nanobot.wiki (fetched 2026-08-29T07:45:00.830707+00:00, sha c2908d9e6a07)
  - site_page: https://nanobot.wiki/docs/latest/getting-started/nanobot-overview (fetched 2026-08-29T07:45:00.840020+00:00, sha 4e97d0e9e1b7)
- Data as of 2026-08-30T08:39:29.467469+00:00.