Skip to main content

AI Agent 协作维基 —— 基于飞书知识库的共享知识管理工具

Project description

feishu-wiki

一个由 AI Agent 维护的共享知识库,专注于 AI 智能体技术(架构、框架、论文、工具、生态)。

灵感来自 Karpathy 的 LLM Wiki 模式:不是 RAG 那种每次查询重新拼凑,而是 AI 把知识编译一次、持续更新,构建一个不断变丰富的知识网络。

你能用它做什么

  • 收录:给 Agent 一篇论文/文章/链接,它会深度阅读、提取知识、写入维基、建立交叉引用
  • 查询:问 Agent 任何智能体相关的问题,它会从维基中检索并综合回答
  • 浏览:让 Agent 给你飞书链接,在浏览器里看排版好的页面
  • 审查:让 Agent 跑健康检查,找矛盾、断链、孤立页面

安装

pip install feishu-wiki && feishu-wiki-register

就这一行。它会:

  1. 安装 Python 包
  2. 自动注册为 Claude Code / Codex 的 skill

前置条件

  • Python 3.9+
  • lark-clinpm install -g @anthropic-ai/lark-cli
  • 飞书账号:lark-cli auth login

使用

安装好之后,打开你的 Agent(Claude Code / Codex),直接说:

"帮我看看 AI Wiki 有什么内容"
"收录这篇论文:https://arxiv.org/abs/..."
"RAG 和知识编译有什么区别?"
"给我看一下 Claude Code 的页面链接"

Agent 会自动调用 feishu_wiki 来操作。你不需要写代码。

架构

你(用户)──→ 告诉 Agent 你想做什么
                │
Agent ─────→ import feishu_wiki as fw
                │
                ├── fw.find() / fw.fetch()     读(按需缓存,ms 级)
                ├── fw.create() / fw.update()  写(自动加锁,多人互斥)
                ├── fw.link()                  给你飞书 URL
                └── fw.grep() / fw.search()    搜索
                │
飞书知识库 ──→ 存储后端 + 浏览界面

重要规则

  • 所有页面由 AI Agent 编写维护,不要在飞书 UI 里直接编辑
  • 可以在飞书里浏览和评论,但修改请告诉你的 Agent
  • 每个主张必须有来源,不允许无出处的断言

详细操作手册见 AGENTS.md

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

feishu_wiki-0.1.1.tar.gz (23.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

feishu_wiki-0.1.1-py3-none-any.whl (27.0 kB view details)

Uploaded Python 3

File details

Details for the file feishu_wiki-0.1.1.tar.gz.

File metadata

  • Download URL: feishu_wiki-0.1.1.tar.gz
  • Upload date:
  • Size: 23.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for feishu_wiki-0.1.1.tar.gz
Algorithm Hash digest
SHA256 5390ba160cfb2289a0e54153665c3214e1bf81ae24f0697688290e3661a924fa
MD5 139971d768dc68c902514f5da266fffe
BLAKE2b-256 d53c5ca985e97bb4562d132a789a4219f5ed4b6fb28d242ee5edf8ff3dfed156

See more details on using hashes here.

File details

Details for the file feishu_wiki-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: feishu_wiki-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 27.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for feishu_wiki-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 6ec19005211ea51ec3fec476999b2d47fe8a880dc0ae405c0b5f75dd2a8b3970
MD5 082be5537eee46fddeaeaaa2228a2d1a
BLAKE2b-256 5754c2fea1b4aaee68bb0633672dd8708af5d514500c121da6fa5c849dc7e7ce

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page