Self-hosted Java/Spring Boot AI assistant platform with multi-user workspaces, multi-provider model failover, an LLM Wiki, MCP and Skills, and IM channel integrations.
agentscope-ai/QwenPaw
A self-hosted personal AI assistant that runs on your machine or in the cloud and connects to chat apps like DingTalk, Lark, Discord and Telegram.
- Stars
- 35,935
- Forks
- 3,200
- Open issues
- 1,124
- Last commit
- 1 hour ago
What is it?
QwenPaw is a personal AI assistant that you deploy yourself, either on your own computer or on a cloud server. It keeps working memory, a full conversation history and a Markdown-based personal knowledge base, and it can schedule recurring tasks such as news digests or report generation.
The assistant can run fully local models through its built-in llama.cpp-based runtime, Ollama or LM Studio, or call more than 14 cloud model providers using an API key. Capabilities are added through Skills, a plugin system with a marketplace, and MCP tool integration. Multiple independent agents can be created, each with its own memory and skills.
Access is available through a web Console, a terminal UI, a desktop app, and channels including DingTalk, Lark, WeChat, Discord, Telegram, iMessage and QQ. Built-in safeguards include a sandbox for shell commands, a tool guard that inspects tool calls, file access restrictions and a skill scanner.
Key features
- 01Three-layer memory with a searchable, editable Markdown knowledge base
- 02Local models via built-in runtime, Ollama or LM Studio, plus 14+ cloud providers
- 03Scheduled tasks and recurring digests
- 04Multi-agent setup with independent memory and skills
- 05Connects to DingTalk, Lark, WeChat, Discord, Telegram and more
- 06Sandbox, tool guard and file guard for safer tool execution
Use cases
- Running a private AI assistant on your own machine without sending data to third-party hosts
- Sending scheduled news digests or reports to DingTalk, Lark or Discord
- Reading, editing and converting documents and code in a project from one workspace
- Managing several specialized agents for different tasks
Topics
FAQ
- What is QwenPaw?
- A self-hosted personal AI assistant that runs on your machine or in the cloud and connects to chat apps like DingTalk, Lark, Discord and Telegram. QwenPaw is a personal AI assistant that you deploy yourself, either on your own computer or on a cloud server. It keeps working memory, a full conversation history and a Markdown-based personal knowledge base, and it can schedule recurring tasks such as news digests or report generation.
- Is QwenPaw free to use? What license does it have?
- QwenPaw is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is QwenPaw still maintained?
- Actively maintained. The last commit to QwenPaw was on Oct 22, 2026.
- What can I use QwenPaw for?
- Running a private AI assistant on your own machine without sending data to third-party hosts Sending scheduled news digests or reports to DingTalk, Lark or Discord Reading, editing and converting documents and code in a project from one workspace Managing several specialized agents for different tasks
- Where can I get QwenPaw?
- The source code and installation instructions are on GitHub: https://github.com/agentscope-ai/QwenPaw
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source personal AI assistant and Agent Harness that plans tasks, runs tools and skills, and keeps memory across web and IM channels.
Open-source multi-agent platform that gives each AI agent its own cloud workspace with filesystem, desktop, browser, network and long-term memory.
LobeHub is a platform for organizing AI agents into always-on teams that can be hired, scheduled, and reviewed from one place.
Self-hosted personal AI agent framework in Python with a browser WebUI, terminal client, chat app channels, tools, memory and MCP support.
Open-source AI personal assistant for planning, writing and personal knowledge, runnable on a Mac or self-hosted with your own model keys.