Kata Containers is an open source project and community working to build a standard implementation of lightweight Virtual Machines (VMs) that feel and perform like containers, but provide the workl…

OpenShell is the safe, private runtime for autonomous AI agents.

CUDA Python: Performance meets Productivity

A Hybrid LLM Inference Gateway for Local GPUs and Cloud APIs

The Open Source Feature Store for AI/ML

Stateful API logic for agentic applications using vLLM

A safetensors extension to efficiently store sparse quantized tensors on disk

A high-performance and light-weight router for vLLM large scale deployment

An LLM post-training framework with vLLM for RL Scaling

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

Common recipes to run vLLM

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Community maintained hardware plugin for vLLM on Apple Silicon

Community maintained hardware plugin for vLLM on Huawei Ascend

Cost-efficient and pluggable Infrastructure components for GenAI inference

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

Copilot-native integrations for Spec Kit across GitHub Copilot CLI, the Copilot App, and VS Code.

SDK for Copilot Agent Engines

Copilot SDK for Java

The official GitHub Copilot plugins collection — MCP servers, skills, hooks, and other extensibility tools for GitHub Copilot.

The GitHub Copilot app is an agent-native desktop experience for finding, running, steering, and landing software work across your GitHub repositories.

Multi-platform SDK for integrating GitHub Copilot Agent into apps and services

GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.

TypeScript/JavaScript SDK for Gemini and Vertex AI.

Temporal Python SDK

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

A simple tool for coordinating several AI agents.

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors