OCR model that handles complex tables, forms, handwriting with full layout.

The absolute trainer to light up AI agents.

"AI-Trader: Can AI Beat the Market?" Live Trading: https://hkuds.github.io/AI-Trader/

🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Spec, benchmarks & reference implementation.

Contexts Optical Compression

The best ChatGPT that $100 can buy.

Example apps for the Apps SDK

Tool for hiding faces in photos and videos using RetinaFace.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

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

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

⚡ Better `pre-commit`, re-engineered in Rust

MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.

🐍 Python package for Open Food Facts

Build resilient language agents as graphs.

🔥 Clone and recreate any website as a modern React app in seconds

Reference PyTorch implementation and models for DINOv3

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

The glamourous AI coding agent for your favourite terminal 💘

My own Prompts for Custom instructions ChatGPT

(CVPR 2025 highlight✨) Official repository of paper "LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models"

A high-performance inference engine for AI models

bluetooth mesh chat, IRC vibes

🚀 The fast, Pythonic way to build MCP servers and clients

The official Python SDK for Model Context Protocol servers and clients

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

An open-source runtime for composable workflows. Great for AI agents and CI/CD.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)