Fully autonomous AI agent system for complex penetration testing tasks.
AI repositories gaining the most stars on GitHub Trending
Fully autonomous AI agent system for complex penetration testing tasks.
Independent auditing of AI agents, verifying in under 120 seconds whether they do what they should.
Makes all software agent-native through a CLI toolchain.
Science agent-skills library with 177 validated skills and 100+ scientific databases for researchers.
2.8T LLM inference with a single 4GB GPU.
The open agent skills tool, installable via npx skills.
Editorial diagram design for coding agents with 44 diagram types in HTML+SVG.
Context window optimization for AI coding agents with sandboxed tool output.
Reverse engineer binaries, apps and runtime behavior with agents.
Use Claude Code, Codex, VSCode, Pi, and OpenCode free with 1.3B+ free tokens.
Official Microsoft inference framework for 1-bit LLMs.
User-friendly AI interface supporting Ollama, OpenAI API, and more.
Tensors and dynamic neural networks in Python with strong GPU acceleration.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's LLM coding observations.
Open source repository of plugins for knowledge workers to use in Claude Cowork.
The model-definition framework for state-of-the-art ML models in text, vision, audio, and multimodal.