freestylefly/WeChatBridge

微信聊天记录一键转发到 AI Agent 与 Obsidian 的原生 macOS 工具

What it solves

WeChatBridge provides a seamless way to export WeChat chat history from macOS to AI agents and local knowledge bases. It solves the friction of manually moving chat records—which WeChat exports as ZIP files containing text, images, and videos—into tools like Claude, ChatGPT, or Obsidian for analysis and archiving.

How it works

The tool leverages the macOS "Share Extension" mechanism. When a user selects multiple chat records in WeChat and uses the "Merge Forward" feature, WeChatBridge appears as a destination in the share menu. It then processes the exported ZIP archive and automatically forwards it to a target application based on the user's selection.

Who it’s for

macOS users who use WeChat for professional or research purposes and want to integrate their chat-based information into AI-powered workflows or personal knowledge management systems.

Highlights

  • Native Integration: Integrates directly into the WeChat share menu with nine built-in entry points.
  • AI Agent Forwarding: Automatically activates target AI apps (e.g., Claude, Codex, Doubao) and pastes the chat archive with optional scene-specific prompts.
  • Obsidian Integration: Creates Markdown notes and saves original attachments, organizing content by chat name.
  • Customizable Targets: Allows users to add any macOS application as a destination.
  • Privacy-First: Operates locally without reading the WeChat database or injecting into the WeChat process; the Share Extension runs in a sandbox without network permissions.
  • Scene & Skill Management: Supports saving specific prompts and managing SKILL.md files to enhance AI agent capabilities for specific group chats.

Related

  • Project
    anyproto/anytype-mcp

    An MCP server that enables AI assistants to interact with Anytype's API, allowing users to manage their knowledge base through natural language conversations.

  • Project
    Yuzzyuk/marketing-os

    A comprehensive set of AI agent skills and modules that transforms LLMs into a professional marketing engine for audits, copy generation, and asset production.

  • Project
    kentjuno/ainovel-cli

    ainovel‑cli is a Go‑based terminal UI that uses a multi‑agent LLM pipeline (Coordinator, Architect, Writer, Editor, Arbiter) to automatically draft long‑form novels. It offers a fully Vietnamese‑localized interface, supports Vietnamese or Chinese output, works offline with local Ollama models or with cloud APIs, and provides rich slash‑command controls for planning, editing, style simulation, import/export, and real‑time steering. The project includes checkpoint recovery, rolling two‑tier planning, and 4‑level context compression to handle very long stories.

  • Project
    leopard627/fire-your-seo-agency

    A Claude Code skill that enables AI agents to audit and optimize websites for search engines and AI answer engines, replacing the need for expensive SEO agencies.