强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

TradingAgents: Multi-Agents LLM Financial Trading Framework

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

A collection of MCP servers.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Welcome to the Ollama Docker Compose Setup! This project simplifies the deployment of Ollama using Docker Compose, making it easy to run Ollama with all its dependencies in a containerized environment

CLI tool for configuring and monitoring Claude Code

🤖 A visualization mcp contains 25+ visual charts using @antvis. Using for chart generation and data analysis.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

A high-throughput and memory-efficient inference and serving engine for LLMs

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Documentation that simply works

GenAI Agent Framework, the Pydantic way

A lightweight, powerful framework for multi-agent workflows

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

A CLI tool for analyzing Claude Code/Codex CLI usage from local JSONL files.

A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)

Build Real-Time Knowledge Graphs for AI Agents

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / veRL/ Swift / Ultra…

verl: Volcano Engine Reinforcement Learning for LLMs

A collection of AI Agents papers (Updated biweekly)

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs