Stars
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A high-throughput and memory-efficient inference and serving engine for LLMs
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
🤗 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.
🤯 LobeHub - an open-source, modern design AI Agent Workspace. Supports multiple AI providers (OpenAI / Claude 4 / Gemini / DeepSeek / Ollama / Qwen), Knowledge Base (file upload / RAG ), one click …
ZITADEL - Identity infrastructure, simplified for you.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Development repository for the Triton language and compiler
📚 Collaborative cheatsheets for console commands
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Simple, safe way to store and distribute tensors
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …
Visualizer for neural network, deep learning and machine learning models
Refine high-quality datasets and visual AI models
Free, local, open-source AI app builder ✨ v0 / lovable / Bolt alternative 🌟 Star if you like it!
CHARM: Composing Heterogeneous Accelerators on Heterogeneous SoC Architecture
LlamaIndex is the leading framework for building LLM-powered agents over your data.
🚀 Efficient implementations of state-of-the-art linear attention models
A collection of example workflows that run on Union
Turns Data and AI algorithms into production-ready web applications in no time.
Fully featured & enhanced replacement for copilot.vim complete with API for interacting with Github Copilot