Starred repositories
Clone any website with one command using AI coding agents
🥷 Engineering habits you already know, turned into skills Claude can run.
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
Intelligent token optimization for Claude Code - achieving 95%+ token reduction through caching, compression, and smart tool intelligence
OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
Create polished screen recordings for free. An open-source alternative to Screen Studio.
Shared intelligence layer for organizations
An open-source, self-hosted AI code review bot powered by Vercel.
A self-hosted email client with an AI agent, running entirely on Cloudflare Workers
Paste any GitHub URL → interactive architecture map. See how files connect, find what breaks if you change something. No install, no accounts — runs entirely in your browser.
Distributed Subagents Framework for Pipecat
from vibe coding to agentic engineering - practice makes claude perfect
Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Multilingual Document Layout Parsing in a Single Vision-Language Model
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
An agentic tool to configure Dockerfiles for any repo
Expect tests your agent's code in a real browser
The agent that grows with you
A multi-hypervisor VM runtime for OCI images, supporting Cloud Hypervisor, Firecracker, QEMU, and Apple Virtualization.framework.
Train the smallest LM you can that fits in 16MB. Best model wins!
Secure, Fast, and Extensible Sandbox runtime for AI agents.
AI agents running research on single-GPU nanochat training automatically