LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

A Next-Generation Training Engine Built for Ultra-Large MoE Models

The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

SGLang is a fast serving framework for large language models and vision language models.

🏡 Open source home automation that puts local control and privacy first.

Build AI Agents, Visually

Ongoing research training transformer models at scale

Streaming data platform. Real-time stream processing, low-latency serving, and Iceberg table management.

Making large AI models cheaper, faster and more accessible

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).

🤯 LobeHub - an open-source, modern design AI Agent Workspace. Supports multiple AI providers, Knowledge Base (file upload / RAG ), one click install MCP Marketplace and Artifacts / Thinking. One-cl…

A simple, performant and scalable Jax LLM!

A JAX-native LLM Post-Training Library

The absolute trainer to light up AI agents.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

💻 A fully functional local AWS cloud stack. Develop and test your cloud & Serverless apps offline

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Simple, scalable AI model deployment on GPU clusters

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Agentic AI system to solve Kaggle Competitions

Scalable toolkit for efficient model reinforcement

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

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

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.