Awesome Opensource Ai

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

Scalable and memory-optimized training of diffusion models

💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.

Ground truth layer for humans and AI agents working together. Version control for knowledge.

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

🌎💪 BrowserGym, a Gym environment for web task automation

The official API server for Exllama. OAI compatible, lightweight, and fast.

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Scalable machine 🤖 learning for time series forecasting.

XAI - An eXplainability toolbox for machine learning

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.

AI-powered code assistant for Vim. OpenAI and ChatGPT plugin for Vim and Neovim.

No description.

Lightning fast data version control system for large repositories of data. Feels like git, pushes and pulls like oxen.

Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

Readymade evaluators for your LLM apps

FAIR Sequence Modeling Toolkit 2

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model. 一个高质量多功能的图像修补模型，可以同时支持插入物体、移除物体、图像扩展、形状可控的物体生成，只需要一个模型

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

Apache YuniKorn Core

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

local multi-agent harness

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

World's first fully integrated and fully Automated Kubernetes management and orchestration solution

Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as a daemon.

Local-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health｜本地优先 Rust TUI/CLI，审计 AI 编程 Agent 会话的成本、Token、延迟、失败与健康度

Self-Programming AI Agent Framework. Agents create and refine their own workflows.

Terminal-native chat client for OpenClaw, Hermes, Ollama and OpenAI-compatible providers. A pure, beautiful terminal chat experience - connect to the gateway, pick an agent, and chat with streaming responses. No fuss, just chat.