Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

Data validation using Python type hints

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Renderer for the harmony response format to be used with gpt-oss

C++ Library Manager for Windows, Linux, and MacOS

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Training Sparse Autoencoders on Language Models

Code release for DynamicTanh (DyT)

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

A lightweight, powerful framework for multi-agent workflows

A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other

FuseAI Project

Testing LLM reasoning abilities with lineage relationship quizzes.

Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)

A library for mechanistic interpretability of GPT-style language models

Wan: Open and Advanced Large-Scale Video Generative Models

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.

DeepEP: an efficient expert-parallel communication library

Muon is Scalable for LLM Training

MoBA: Mixture of Block Attention for Long-Context LLMs

Democratizing Reinforcement Learning for LLMs

The OpenAI Model Spec