# agentscope-ai/QwenPaw

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Repository: https://github.com/agentscope-ai/QwenPaw
Canonical: https://ross.abutalabs.com/products/qwenpaw
Homepage: http://qwenpaw.agentscope.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, llm-tools, llms, skills, agentscope, agent-harness, harness-engineering, super-agent, loop-engineering, ai-agent, ai-agents, chatbot, personal-ai-assistant, self-hosted, webui, mcp
Last push: 2026-08-26T15:46:46+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 97, longevity 13
- inputs: {"age_days": 190, "days_push": 7, "days_rel": 20, "gap_med": 2, "n_releases_24m": 48}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 34508, forks 3037 (observed 2026-08-28T04:12:00.613319+00:00)

## What it is
QwenPaw is a self-hosted personal AI assistant built in Python that connects to multiple chat channels (DingTalk, Feishu, QQ, Discord, iMessage) and runs scheduled tasks. Its capabilities are driven by an extensible Skills system with built-in skills for cron scheduling, PDF/Office handling, news digests, and file reading, plus MCP support.

## Use cases
- run a personal ai assistant on my own machine
- chat with an ai assistant over discord or dingtalk
- schedule automated tasks with an llm agent
- self-hosted chatgpt alternative with custom skills
- extend an ai assistant with mcp tools
- automate pdf and office document handling via chat

## When to choose
- you want a personal assistant that keeps all data on your own machine
- you need to reach the assistant through chat apps you already use
- you want to extend capabilities with custom skills or MCP tools
- you need scheduled/cron-driven LLM tasks

## When to avoid
- you need a fully managed hosted assistant with no setup
- you want a simple single-channel chatbot with minimal footprint
- you need non-Python integration or a lightweight embedded agent

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, chatbot, mcp, scheduling, workflow-automation, chat-interface
- domain: chatbots, large-language-models, self-hosted, developer-tools
- platform: python, self-hosted, cross-platform, cloud
- tags: personal-ai-assistant, skills, multi-channel, agent-harness, webui, llm-tools, ai-agents, automation, docker, discord, telegram

## Member repositories
- agentscope-ai/QwenPaw (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:00.613319+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 2026-08-29T16:27:29.107035+00:00, confidence not recorded.
  - readme: https://github.com/agentscope-ai/QwenPaw (fetched 2026-08-28T04:12:00.613319+00:00, sha 915f8a2d6e27)
  - homepage: http://qwenpaw.agentscope.io/ (fetched 2026-08-29T07:48:13.991772+00:00, sha f7d051e81abb)
  - registry_pypi: https://pypi.org/pypi/qwenpaw/json (fetched 2026-08-29T07:48:14.001117+00:00, sha 92848a58273c)
- Data as of 2026-08-30T08:39:29.467469+00:00.