GitHub Trending

opendatalab/MinerU — Transforms complex documents like PDFs and Office docs into LLM-ready markdown/J

31 sec read13 views0 listens

72,103 stars | 5,839 forks | Python

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

What it does

MinerU is a high-accuracy document parsing engine that converts complex documents into structured Markdown/JSON, essential for AI workflows like RAG and agent systems. It supports multiple languages and integrates with various development frameworks.

Why it matters: Transform your documents into LLM-friendly formats effortlessly with MinerU! 🚀 #MinerU #AI

View on GitHub

Trending today with 380 new stars

Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.

MemPalace/mempalace — The best-benchmarked open-source AI memory system. And it's free.

53,741 stars | 7,073 forks | Python The best-benchmarked open-source AI memory system. And it's free. What it does MemPalace is an open-source AI memory system that stores conversation history verbatim and retrieves it with semantic search, offering ...

Ali Nemati

GitHub TrendingMay 531 sec read

Arindam200/awesome-ai-apps — A collection of projects showcasing RAG, agents, workflows, and other AI use cas

10,950 stars | 1,453 forks | Python A collection of projects showcasing RAG, agents, workflows, and other AI use cases What it does This repository offers a wide range of practical examples and tutorials for developers to build AI-powered application...

Ali Nemati

GitHub TrendingMay 431 sec read

cocoindex-io/cocoindex — Incremental engine for long horizon agents 🌟 Star if you like it!

7,785 stars | 576 forks | Python Incremental engine for long horizon agents 🌟 Star if you like it! What it does CocoIndex is an incremental engine that keeps AI agents and LLM applications updated with fresh, continuous context from various data sour...

Ali Nemati

GitHub TrendingApr 2728 sec read

deepseek-ai/DeepSeek-V3

103,013 stars | 16,694 forks | Python What it does DeepSeek-V3 is a highly efficient and cost-effective large language model with 671B parameters, featuring innovative load balancing and multi-token prediction strategies. It outperforms other open-so...

Ali Nemati

GitHub TrendingMar 634 sec read

QwenLM/Qwen-Agent — Agent framework and applications built upon Qwen>=3.0, featuring Function Callin

14,262 stars | 1,354 forks | Python Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc. What it does Qwen-Agent is a Python framework for building LLM applications w...

Ali Nemati

opendatalab/MinerU — Transforms complex documents like PDFs and Office docs into LLM-ready markdown/J

What it does

Related Articles

MemPalace/mempalace — The best-benchmarked open-source AI memory system. And it's free.

Arindam200/awesome-ai-apps — A collection of projects showcasing RAG, agents, workflows, and other AI use cas

cocoindex-io/cocoindex — Incremental engine for long horizon agents 🌟 Star if you like it!

deepseek-ai/DeepSeek-V3

QwenLM/Qwen-Agent — Agent framework and applications built upon Qwen>=3.0, featuring Function Callin