The collaboration layer for AI teams: domain experts annotate and review agent behavior, engineers improve the agent from what they find.

Gas Town - multi-agent workspace manager

This repository provides a multi-modal RAG (Retrieval-Augmented Generation) solution that processes documents visually using late interaction embedding techniques.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

💫 Toolkit to help you get started with Spec-Driven Development

Python package that aligns LLM judges with human scores

Fixes compatibility issues with older games running on Windows 10/11 by wrapping DirectX dlls. Also allows loading custom libraries with the file extension .asi into game processes.

VSCode extension for evaluating Copilot Chat

Task-Aware Agent-driven Prompt Optimization Framework

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

Showcase of a line-of-business agent with evaluation framework

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

Sample for an AI orchestrated workflow

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

🍦 Never use print() to debug again.

Azure DevOps Python API

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

TypeChat is a library that makes it easy to build natural language interfaces using types.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

Promptflow experimentation framework

tiktoken is a fast BPE tokeniser for use with OpenAI's models.