#
Starred repositories
The AI coding agent built for the terminal.
Robust Speech Recognition via Large-Scale Weak Supervision
Spec-driven development for AI coding assistants.
Finite state machine class generator for java, exports graphml, supports immutability!
Wan: Open and Advanced Large-Scale Video Generative Models
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.
Run the latest LLMs and VLMs across GPU, NPU, and CPU with PC (Python/C++) & mobile (Android & iOS) support, running quickly with OpenAI gpt-oss, Granite4, Qwen3VL, Gemma 3n and more.
Revert makes it incredibly easy to build integrations with any third party API
🚀 The fast, Pythonic way to build MCP servers and clients
The official PyTorch implementation of recent paper - SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
⚡ TabPFN: Foundation Model for Tabular Data ⚡
Reference PyTorch implementation and models for DINOv3
Restate is the platform for building resilient applications that tolerate all infrastructure faults w/o the need for a PhD.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Open source version of Anthropic's Clio: A system for privacy-preserving insights into real-world AI use
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
SkyReels-V2: Infinite-length Film Generative model
DataRubrics, a structured framework for assessing the quality of both human- and model-generated datasets. Leveraging recent advances in LLM-based evaluation.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.