User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.

The absolute trainer to light up AI agents.

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!

An interface library for RL post training with environments.

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

Windows inside a Docker container.

Local-first AI Notepad for Private Meetings

A Quirky Assortment of CuTe Kernels

The LLM Evaluation Framework

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

#1 Locally hosted web application that allows you to perform various operations on PDF files

Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

Running Docling as an API service

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment…

ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)

ArcticInference: vLLM plugin for high-throughput, low-latency inference

CUDA Python: Performance meets Productivity

PyTorch native post-training library

Supercharge Your LLM Application Evaluations 🚀

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Firmware replacement for Growatt ShineWiFi-S

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

🤗 smolagents: a barebones library for agents that think in code.

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

An extremely fast Python package and project manager, written in Rust.

Get your documents ready for gen AI

Material for gpu-mode lectures

PyTorch native quantization and sparsity for training and inference