🙌 OpenHands: Code Less, Make More

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Ongoing research training transformer models at scale

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

Open-source framework for the research and development of foundation models.

A simple, performant and scalable Jax LLM!

⚡A CLI tool for code structural search, lint and rewriting. Written in Rust

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

Servo aims to empower developers with a lightweight, high-performance alternative for embedding web technologies in applications.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Extremely fast Query Engine for DataFrames, written in Rust

Async RL Training at Scale

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data

slime is an LLM post-training framework for RL Scaling.

Development repository for the Triton language and compiler

A JAX-native LLM Post-Training Library

Environments for LLM Reinforcement Learning

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic last-mile 🪁

Managed Agent Posttraining

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)

🌐 The open-source Agentic browser; privacy-first alternative to ChatGPT Atlas, Perplexity Comet, Dia.

Scalable data pre processing and curation toolkit for LLMs

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!