{"data":{"slug":"agentscope-ai-qwenpaw","name":"QwenPaw","tagline":"Your Personal AI Assistant","github_url":"https://github.com/agentscope-ai/QwenPaw","owner":"agentscope-ai","repo":"QwenPaw","owner_avatar_url":"https://avatars.githubusercontent.com/u/211762292?v=4","primary_language":"Python","stars":21270,"forks":2743,"topics":["agent","agent-harness","agentscope","harness-engineering","llm-tools","llms","skills","super-agent"],"archived":false,"github_pushed_at":"2026-07-07T11:06:31+00:00","url":"https://www.graphcanon.com/tools/agentscope-ai-qwenpaw","markdown_url":"https://www.graphcanon.com/tools/agentscope-ai-qwenpaw.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agentscope-ai-qwenpaw","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agentscope-ai-qwenpaw","description":"Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.","homepage_url":"http://qwenpaw.agentscope.io/","license":"Apache-2.0","open_issues":903,"watchers":99,"ai_summary":"QwenPaw is a personal AI assistant that can be deployed locally or on the cloud. It supports multiple chat applications and includes features such as multi-agent capabilities, security measures like kernel-level sandboxes, extensible skills and plugins marketplace, coding mode with integrated web IDE, and more.","readme_excerpt":"
\n\n# QwenPaw\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\"agentscope-ai%2FQwenPaw\n\n[[Documentation](https://qwenpaw.agentscope.io/)] [[中文](README_zh.md)] [[日本語](README_ja.md)] [[Русский](README_ru.md)]\n\n

\n \"QwenPaw\n

\n\n

Works for you, grows with you.

\n\n
\n\nYour personal AI assistant — deploy locally or in the cloud, extend with Skills & Plugins, connect across every channel.\n\n| | |\n| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| **Never forgets** | Three-layer memory — live working context, full verbatim history, and distilled knowledge. Older turns evict but stay recallable on demand; nothing is summarized away or lost. |\n| **Local or cloud, runs free** | QwenPaw-Flash models (2B / 4B / 9B) trained for agent tasks. Built-in QwenPaw Local runtime — no API key, no cloud dependency. Also works with Ollama, LM Studio, or 14+ cloud providers. |\n| **Security built in** | Kernel-level Sandbox, Tool Guard, File Guard, Skill Scanner, and Access Policy. Dangerous commands are blocked before they run. |\n| **Multi-agent & parallel** | Spawn independent agents with their own memory and skills. Sub-agents at runtime. Agent Communication Protocol (ACP) for cross-system orchestration. |\n| **Coding Mode** | Three-panel Web IDE with file tree, diff preview, and chat. Jump-to-definition, find-references, and structural code search built in. |\n| **Extensible** | Skills for scheduling, documents, browser, news, and more. Plugin architecture with a marketplace. MCP integration for external tools. Combine them into purpose-built workflows. |\n| **Reachable anywhere** | DingTalk, Lark, WeChat, Discord, Telegram, iMessage, QQ — one instance, all channels. Console, TUI, and desktop app for direct access. |\n| **Yours, not ours** | Deploy locally — data stays on your machine. No third-party hosting, no data upload. |\n\n
\nWhat you can do with QwenPaw\n\n
\n\n- **Automation & scheduling**: Set up recurring tasks — news digests, report generation, multi-channel broadcasting — all on your schedule.\n- **Code & development**: Read, edit, review, and test code in your projects; Coding Mode helps you quickly find and understand code.\n- **Document processing**: Read, write, and convert PDF, Word, Excel, and PowerPoint files.\n- **Information gathering**: Search the web, follow subscriptions, summarize videos, and find what you need in your personal knowledge base.\n- **Multi-channel ops**: Push alerts, summaries, or AI-generated content to DingTalk, Lark, Discord, Telegram, and more — simultaneously or per channel.\n- **Custom workflows**: Combine built-in capabilities, plugins, and scheduled tasks into workflows tailored to your needs.\n\n
\n\n---\n\n## News\n\n- [2026-06-17] **v1.1.12 — Models Page Overhaul & Simple Mode** | Redesigned Models page with provider aggregation; new Simple Mode for streamlined navigation.\n\n | Highlight | What's new |\n |-----------|------------|\n | **Models Page Overhaul** | Provider Aggregation, Unified Ca","github_created_at":"2026-02-24T03:42:56+00:00","created_at":"2026-07-07T17:38:31.495516+00:00","updated_at":"2026-07-07T19:45:43.593706+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"llms","name":"llms"},{"slug":"harness-engineering","name":"harness-engineering"},{"slug":"agentscope","name":"agentscope"},{"slug":"llm-tools","name":"llm-tools"},{"slug":"skills","name":"skills"},{"slug":"agent-harness","name":"agent-harness"},{"slug":"agent","name":"agent"}]}}