Run models like Kimi-K2.5, GLM-5, DeepSeek, gpt-oss, Gemma, Qwen etc.
Port of Facebook's LLaMA model in C/C++
Prompt, run, edit, and deploy full-stack web applications
AI edge infrastructure for macOS. Run local or cloud models
Prompt, run, edit, & deploy full-stack web applications using any LLM
Desktop app for prototyping and debugging LangGraph applications
Orchestrate coding agents remotely from your phone, desktop and CLI
Vector Database for the next generation of AI applications
MemU is an open-source memory framework for AI companions
Python inference and LoRA trainer package for the LTX-2 audio–video
Evaluation and Tracking for LLM Experiments
AIHawk aims to easy job hunt process by automating job applications
Official code repo for the O'Reilly Book
Low-code app builder for RAG and multi-agent AI applications
Wan2.1: Open and Advanced Large-Scale Video Generative Model
Helps developers deploy LangChain runnables and chains as a REST API
C++ library for high performance inference on NVIDIA GPUs
The free, Open Source alternative to OpenAI, Claude and others
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
⚡ Building applications with LLMs through composability ⚡
Emscripten: An LLVM-to-WebAssembly Compiler
Defang CLI and sample projects
Building applications with LLMs through composability
Local, policy-gated signing and wallet management for every chain
Official inference repo for FLUX.1 models