🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

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

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

LLM inference in C/C++

Tensor library for machine learning

SGLang is a fast serving framework for large language models and vision language models.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Visual Studio Code

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

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

A generative world for general-purpose robotics & embodied AI learning.

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

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

A framework for few-shot evaluation of language models.

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

verl: Volcano Engine Reinforcement Learning for LLMs

The official Python SDK for Model Context Protocol servers and clients

Environments for LLM Reinforcement Learning

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

PyTorch native post-training library

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

SkyRL: A Modular Full-stack RL Library for LLMs

Democratizing Reinforcement Learning for LLMs

An Open Source Machine Learning Framework for Everyone

AllenAI's post-training codebase

Scalable toolkit for efficient model reinforcement