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.

What it solves

QwenPaw is a personal AI assistant designed to be deployed locally or in the cloud, providing a secure, extensible, and multi-channel interface for automating tasks, managing personal knowledge, and interacting with files and external tools.

How it works

It operates as an "Agent OS" architecture that manages resources, governance (security policies), and sandboxes across different operating systems. It uses a three-layer memory system (live context, verbatim history, and a self-evolving personal knowledge base via ReMe) to ensure it never forgets. The system supports local runtimes (QwenPaw-Flash models) or integration with 14+ cloud providers and local tools like Ollama and LM Studio. It connects to various communication channels (e.g., Discord, Telegram, WeChat) via an Agent Communication Protocol (ACP).

Who it’s for

It is for individuals who want a private, highly customizable AI assistant that can handle complex workflows, manage local files, and be reachable across multiple messaging platforms without relying solely on third-party cloud hosting.

Highlights

  • Three-layer Memory: Combines live context, full history, and a self-evolving Markdown-based knowledge base.
  • Agent OS Architecture: Features a kernel-level sandbox, tool guards, and a unified file workspace for editing and reviewing code/documents.
  • Multi-channel Reachability: Single instance integration with DingTalk, Lark, WeChat, Discord, Telegram, and iMessage.
  • Local-First Privacy: Option to deploy entirely locally so data stays on the user's machine.
  • Extensible Ecosystem: Plugin architecture with a marketplace and MCP integration for external tools.
  • Multi-agent Capabilities: Ability to spawn independent sub-agents with their own memory and skills at runtime.

Related

  • Project
    pocketpaw/pocketpaw

    A self-hosted AI agent that runs locally on your machine, providing a native desktop app and integration with multiple messaging platforms like Discord and Slack.

  • Project
    ownpilot/OwnPilot

    A privacy-first, self-hosted AI assistant platform featuring autonomous agents, 250+ tools, and integrations for IoT, browser automation, and messaging apps.

  • Project
    ClawRunr/JavaClaw

    A Java-based personal AI assistant that runs locally to manage tasks, execute shell commands, and interact via Telegram, Discord, or a web UI.

  • Project
    ShenSeanChen/waku-agent

    A local-first personal AI assistant and readable blueprint that demonstrates the core pillars of agentic loops, memory management, and LLM-Ops without using complex frameworks.

  • Project
    Superagentsys/novalclaw

    A local-first AI agent platform with a Rust core and desktop interface that allows users to build personalized agents with MBTI-driven personalities and multi-channel deployment.