🏆 #5,836 overall#1265 of 1,494 in Search & Retrieval

Nebutra /MinerU-Skill

AI-Native document parser: PDF, Office & images → clean Markdown with LaTeX, tables & OCR. Zero-dependency CLI & skill for Claude Code, Cursor & AI agents.

$ git clone https://github.com/Nebutra/MinerU-Skill.git
GitHub social preview for Nebutra/MinerU-Skill
Stars
133
133
This week
—
Forks
6
6
Language
Python
License
MIT
Created
Feb 13, 2026
0.7 years old
Last push
Sep 24, 2026

Categories

GitHub topics

More in Search & Retrieval

Search & Retrieval

SylphxAI/anymd🔥 active

▲ +3 ★ this week

Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.

📄 OCR & Documents
RustMITupdated Nov 7, 2026
GitHub ↗★ 1.1K⑂ 93
Search & Retrieval

Snailclimb/AIGuide

AI 应用开发、AI 编程实战与面试指南,涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。

Otherno licenseupdated Nov 6, 2026
GitHub ↗★ 745⑂ 84
Search & Retrieval

docsagent/docsagent

▲ +2 ★ this week

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, local docs on the road). Native C++ search core: BM25 + passage ranking in ~15 ms. MCP server for Claude, Cursor, Cline & any MCP client.

TypeScriptno licenseupdated Sep 28, 2026
GitHub ↗★ 580⑂ 10
Search & Retrieval

oleksiijko/pmb🔥 active

▲ +5 ★ this week

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

🧬 Embeddings
PythonApache-2.0updated Nov 11, 2026
GitHub ↗★ 288⑂ 34
Search & Retrieval

codecoradev/uteke🔥 active

▲ +2 ★ this week

Long-term memory for AI agents (MCP). One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Works with Claude Code, Cursor, Codex. Self-host free or use Uteke Cloud.

RustApache-2.0updated Nov 13, 2026
GitHub ↗★ 286⑂ 31
Search & Retrieval

yfedoseev/office_oxide🔥 active

The fastest Office document library for Python, Rust, Go, JS/TS, C# and WASM. DOCX, XLSX, PPTX, DOC, XLS, PPT. Up to 100× faster than python-docx/openpyxl/python-pptx. 100% pass rate on valid Office files. MIT/Apache-2.0.

RustApache-2.0updated Nov 11, 2026
GitHub ↗★ 164⑂ 25

Data from GitHub · snapshot Nov 13, 2026