Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

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

An extremely fast Python linter and code formatter, written in Rust.

The uncompromising Python code formatter

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Fully open reproduction of DeepSeek-R1

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

Nano vLLM

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

qwen-code is a coding agent that lives in digital world.

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped to handle complex agentic tasks.

verl: Volcano Engine Reinforcement Learning for LLMs

论文就是你所需要的。

A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Memory infrastructure for LLMs and AI agents

Convert HTML to Markdown

A lightweight, powerful framework for multi-agent workflows

UltraRAG v2: A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

MiroThinker is a series of open-source agentic models trained for deep research and complex tool use scenarios.

AgentEvolver: Towards Efficient Self-Evolving Agent System

Rich is a Python library for rich text and beautiful formatting in the terminal.

AdalFlow: The library to build & auto-optimize LLM applications.