Metadata-Version: 2.4
Name: omniseek
Version: 0.3.0
Summary: Give your AI agent the parts of the internet web search doesn't reach: podcasts and videos, Chinese communities, and research papers. An MCP server for Claude Code, Cursor, and Codex.
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/Battam1111/omniseek
Project-URL: Repository, https://github.com/Battam1111/omniseek
Project-URL: Issues, https://github.com/Battam1111/omniseek/issues
Project-URL: Changelog, https://github.com/Battam1111/omniseek/blob/main/CHANGELOG.md
Project-URL: Documentation, https://github.com/Battam1111/omniseek#readme
Keywords: mcp,ai-agent,claude-code,cursor,llm,rag,citation-graph,transcription,podcast-transcription,bilibili,zhihu,self-hosted
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
License-File: NOTICE
Requires-Dist: mcp[cli]<2,>=1.0.0
Requires-Dist: sniffio>=1.3
Requires-Dist: semanticscholar>=0.10.0
Requires-Dist: praw>=7.7.0
Requires-Dist: atproto>=0.0.55
Requires-Dist: playwright>=1.40
Requires-Dist: httpx>=0.27
Requires-Dist: beautifulsoup4>=4.12
Requires-Dist: lxml>=5.0
Requires-Dist: feedparser>=6.0
Requires-Dist: markdownify>=0.13
Requires-Dist: pyyaml>=6.0
Requires-Dist: curl_cffi>=0.7
Requires-Dist: pydantic>=2.5
Requires-Dist: platformdirs>=4.0
Requires-Dist: python-dateutil>=2.8
Requires-Dist: tenacity>=9.0
Requires-Dist: yt-dlp>=2026.8.19
Requires-Dist: youtube-transcript-api>=0.6.2
Requires-Dist: python-pptx>=1.0
Requires-Dist: python-docx>=1.1
Requires-Dist: openpyxl>=3.1
Requires-Dist: pillow>=10.0
Requires-Dist: numpy>=1.26
Provides-Extra: pdf
Requires-Dist: pymupdf>=1.24; extra == "pdf"
Provides-Extra: asr
Requires-Dist: funasr>=1.0; extra == "asr"
Requires-Dist: imageio-ffmpeg>=0.5; extra == "asr"
Provides-Extra: recall
Requires-Dist: sentence-transformers>=3.0; extra == "recall"
Provides-Extra: ocr
Requires-Dist: rapidocr-onnxruntime>=1.2; extra == "ocr"
Provides-Extra: walled
Requires-Dist: patchright>=1.40; extra == "walled"
Requires-Dist: xhshow>=0.1.0; extra == "walled"
Provides-Extra: all
Requires-Dist: pymupdf>=1.24; extra == "all"
Requires-Dist: funasr>=1.0; extra == "all"
Requires-Dist: imageio-ffmpeg>=0.5; extra == "all"
Requires-Dist: patchright>=1.40; extra == "all"
Requires-Dist: xhshow>=0.1.0; extra == "all"
Requires-Dist: sentence-transformers>=3.0; extra == "all"
Requires-Dist: rapidocr-onnxruntime>=1.2; extra == "all"
Dynamic: license-file

<!-- mcp-name: io.github.Battam1111/omniseek -->
<!-- Generated from README.md by scripts/gen_pypi_readme.py: edit README.md, then run it. -->

<p align="center">
  <img src="https://raw.githubusercontent.com/Battam1111/omniseek/main/assets/logo-lockup.png?v=2026-10-11b" width="320" alt="OmniSeek">
</p>

**Give your AI agent the parts of the internet web search doesn't reach.**

OmniSeek is an add-on for AI assistants and agents like Claude Code, Cursor, and Codex that lets them search where web search stops.

- Ask in English, get what people actually said on Bilibili, and Zhihu when you ask for it, with links to the original posts.
- Get the papers a research field is built on, and the recent ones building on them, in one answer.
- Have your agent watch a topic and tell you only what is new since last time.

```bash
uv tool install omniseek
claude mcp add omniseek -- omniseek
```

Runs on your own computer. It plugs in through MCP, the standard way AI apps like Claude Code and Cursor add tools. Cursor and Codex: one line each, see [Install](https://github.com/Battam1111/omniseek/blob/main/docs/install.md#connect-your-client).

[![CI](https://github.com/Battam1111/omniseek/actions/workflows/ci.yml/badge.svg)](https://github.com/Battam1111/omniseek/actions/workflows/ci.yml) [![PyPI](https://img.shields.io/pypi/v/omniseek?color=3B82F6&style=flat-square)](https://pypi.org/project/omniseek/) [![License](https://img.shields.io/badge/License-Apache_2.0-3B82F6?style=flat-square)](https://github.com/Battam1111/omniseek/blob/main/LICENSE) ![Python](https://img.shields.io/badge/Python_3.11+-3B82F6?style=flat-square) ![Built for MCP](https://img.shields.io/badge/built_for-MCP-3B82F6?style=flat-square)
**Languages:** English · [中文](https://github.com/Battam1111/omniseek/blob/main/docs/i18n/README_zh.md) · [日本語](https://github.com/Battam1111/omniseek/blob/main/docs/i18n/README_ja.md)

---

## See the difference

We asked two agents for Mu Li's exact words on the Transformer paper's writing, and the minute, in his 87-minute Bilibili walkthrough: web search returned a paraphrase and "around minutes 1 to 8", while the agent with OmniSeek transcribed the video and found the line at 1:21:51.

<p align="center">
  <img src="https://raw.githubusercontent.com/Battam1111/omniseek/main/assets/demo/compare-en-light.gif?v=2026-10-11d" width="720" alt="A real run, side by side. Left, an agent with web search only answers with a paraphrase and says around minutes 1 to 8. Right, an agent with OmniSeek transcribes the 87-minute video and quotes Mu Li at 1:21:51, with a link that opens there.">
</p>

[The full comparison on three questions](https://github.com/Battam1111/omniseek/blob/main/docs/compare.md), with sources, dates, and a short video.
