K0nd1us/QQ-agent

立志做使用起来最简单能实现的功能最全面的LLM机器人。

What it solves

QQ Agent provides a local AI assistant for QQ conversations. It handles model interaction, session management, memory, persona settings, web searching, and plugin-based feature extensions. The project is currently split into two versions: a stable baseline (0.4) and an ongoing architectural rewrite (0.5) to improve modularity and resource management.

How it works

The project connects to QQ via the OneBot v11 protocol, which users must install and configure independently. The agent acts as the application layer, processing messages and executing logic. Version 0.5 introduces a "thin kernel" architecture where components are clearly defined, allowing for better component replacement, standardized SDK-based extension development, and more reliable resource cleanup during startup or failure.

Who it’s for

It is for users who want to run a local, customizable AI assistant on QQ. Version 0.4 is recommended for those who need a stable, existing baseline. Version 0.5 is intended for developers or users interested in testing the new, more modular architecture, though it is currently unfinished and requires manual verification of features.

Highlights

  • Dual-version structure: Separates the stable baseline (0.4) from the ongoing architectural rewrite (0.5) to prevent breaking changes.
  • Modular architecture: Version 0.5 focuses on clear boundaries between core services, frontend panels, and plugins to reduce inter-module dependencies.
  • Extensible design: Supports plugins and skills with defined SDKs, permission boundaries, and lifecycle management.
  • Protocol-agnostic: Uses OneBot v11 to interface with QQ, allowing users to manage their own protocol-side installations and credentials.
  • Resource control: Improves how components and extensions manage resources to prevent memory leaks or lingering tasks.

Related

  • Project
    pinganbbOvO/ai-companion-kit

    AI Companion Kit is a collection of modular tools that give a chat AI human-like memory, typing behavior, and the ability to control a smartphone and post to QQ Zone on its own. It solves the two common shortcomings of AI assistants: they feel robotic and they can't interact with the real world beyond text.

  • Project
    Pinvou/pinvou-agent

    Pinvou Agent is a cross‑platform desktop AI workspace built with Tauri 2, React and a Rust‑based agent engine (CodeWhale). It lets users attach files, run local or cloud LLMs, and use extensible tools to turn chat prompts into real deliverables—documents, designs, or code—while keeping data private when desired.

  • Project
    fuyuxiang/echo-agent

    Echo Agent is an open‑source, self‑hosted AI‑agent runtime that provides long‑term memory, automatic skill extraction/evolution, and pluggable tool integration. It can run interactively in a terminal, as a long‑living Gateway service with a web dashboard and API, or be embedded in a desktop application (EchoAgent Desktop). The core runtime manages the agent loop, session context, model routing, permissions, and automation channels, while the memory system recalls past facts and the evolution system turns execution traces into reusable Skills. Install via `pip install "echo-agent[all]"`, configure an LLM API key, and start with `echo-agent run` or `echo-agent gateway`.

  • Project
    Derpyu520/qq-bridge

    A Node.js bridge that connects QQ (via SnowLuma OneBot v11) to a DeepSeek Harness AI agent, providing chat, tool calls, role‑play, token‑usage dashboard, and a web console.

  • Project
    liliMozi/openhanako

    A user-friendly AI agent desktop application that provides personalized assistants with memory, personality, and the ability to operate a computer and browse the web.