Generate Pydantic models and other types from Supabase/Postgres/MySQL schemas automatically. Ideal for FastAPI, Supabase, and rapid prototyping.

Copy & Paste React components to build modern web applications.

Convert PDF to markdown + JSON quickly with high accuracy

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

FastAPI Best Practices and Conventions we used at our startup

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

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

A collection of learning resources for curious software engineers

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Large Language Model Text Generation Inference

Useful resources for creating apps with Electron

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

An open source application built using the new router, server components and everything new in Next.js 13.

A browser extension for automating your browser by connecting blocks

Interact, analyze and structure massive text, image, embedding, audio and video datasets

Large batch training of CTR models based on DeepCTR with CowClip.

docTTTTTquery document expansion model

A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

🧩 The Browser Extension Framework

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Pythonic AI generation of images and videos

📖 Paper reading list in conversational AI.

Stable Diffusion web UI

This project is deprecated. Check my new project ChatHub:

Weaviate connector for Apache Spark

AI magics meet Infinite draw board.

✨😂 2000+ ways to add design flair, user delight, and whimsy to your product.

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.