teng-lin/weread-omni

微信读书（WeRead）增强工具包：集成 Agent、API、SDK、CLI 与插件，内置 40 项操作；支持阅读微信公众号、书架与笔记读写、书籍导入及 AI 权限。

What it solves

weread-omni provides a comprehensive, non-official SDK and command-line interface (CLI) for WeChat Reading (微信读书), expanding the platform's capabilities far beyond the official Agent Skill. While the official skill is limited to six read-only operations, this project enables over 40 read-write operations, allowing users to automate their reading workflow, manage their library, and integrate WeChat Reading data into AI agents.

How it works

The project is built on the API used by WeChat Reading's E-ink screen devices. It offers three primary ways to interact with the service:

  1. CLI: A command-line tool that can output JSON for easy integration with other scripts.
  2. TypeScript SDK: A fully typed library for developers to build applications.
  3. Agent Skill: A pre-configured skill that allows AI agents (like Codex or Claude Code) to check login status, perform read/write operations, and handle pagination.

Users authenticate via a QR code scan using their WeChat Reading account. The tool also maintains a local content library (using SQLite WAL) to cache book information, chapters, and public account articles to reduce redundant network requests.

Who it’s for

  • Developers wanting to build apps or automations around their WeChat Reading data.
  • AI Agent users who want their AI assistants to interact with their books, notes, and highlights.
  • Power users who want to export public account feeds, import personal books (EPUB, PDF, etc.), or manage their reading lists via terminal.

Highlights

  • Extended Capabilities: Supports adding, modifying, and deleting highlights and reviews, which are not possible via official skills.
  • Content Import: Allows importing personal files in EPUB, PDF, MOBI, TXT, and AZW3 formats.
  • Public Account Integration: Ability to read articles, subscribe to accounts, and export feeds in RSS, Atom, or JSON formats.
  • AI Integration: Direct access to the "WeChat Reading AI" to ask questions about specific books.
  • Local Caching: Built-in local library to store content and avoid repeated downloads.

Related

  • Project
    imraywang/wewrite

    A comprehensive AI content creation skill for WeChat Official Accounts that automates topic selection, evidence-based writing, editorial review, and professional layout formatting.

  • Project
    aiworkskills/wechat-article-skills

    An open-source AI agent skill set that automates the entire WeChat Official Account workflow from topic selection and writing to HTML formatting and publishing.

  • Project
    zhimaAi/chatwiki

    A workflow automation platform that turns WeChat Official Accounts into AI agents with drag-and-drop workflows and integrated knowledge bases.

  • Project
    geekjourneyx/md2wechat-skill

    md2wechat is a Go‑based CLI that converts Markdown into WeChat public‑account HTML, offers advanced layout modules, image generation, multi‑account handling, and a JSON‑driven discovery interface for AI agents. It works in a free “prompt‑only” mode or a paid Professional API mode that returns final HTML.

  • Project
    ShenSeanChen/waku-agent

    A local-first personal AI assistant with a transparent, lightweight codebase that implements core agent pillars like memory, loops, and evaluation.