🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

🙌 OpenHands: Code Less, Make More

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

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

A toolkit for developing and comparing reinforcement learning algorithms.

The best ChatGPT that $100 can buy.

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

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

DSPy: The framework for programming—not prompting—language models

An open-source RAG-based tool for chatting with your documents.

Contexts Optical Compression

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Public repository for Skills

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

verl: Volcano Engine Reinforcement Learning for LLMs

Ongoing research training transformer models at scale

A hyperparameter optimization framework

Minimal reproduction of DeepSeek R1-Zero

Supercharge Your LLM Application Evaluations 🚀

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

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!

A fast PostgreSQL Database Client Library for Python/asyncio.

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …