Lists (1)
Starred repositories
CLI-Anything: Making ALL Software Agent-Native
Use Garry Tan's exact Claude Code setup: 6 opinionated tools that serve as CEO, Eng Manager, Release Manager and QA Engineer
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line …
MCP is the protocol for tool access. We're the virtualization layer for context.
Training neural networks on Apple Neural Engine via reverse-engineered private APIs
smartKNN - A feature-weighted KNN algorithm with automatic preprocessing, normalization, and learned feature importance.
Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating inaccessible code.
An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to exploitation to post-exploitation, with zero human intervention.
Ghidra is a software reverse engineering (SRE) framework
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Some setup scripts for security research tools.
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
Use Claude Code from your phone — or anywhere — over a secure VPN connection.
Collection of leaked system prompts
Self-learning data agent that grounds its answers in 6 layers of context. Inspired by OpenAI's in-house implementation.
Simple cross-platform colored terminal text in Python
Uploader + CSV parser + raw file preview + UI for custom user column mapping, all in one
📄 PDF ->.MD/.JSON API & SDK for PaddleOCR-VL with structured data extraction. Self-hostable.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
omo; the best agent harness - previously oh-my-opencode
Flexible tool to build planet-scale vector tilesets from OpenStreetMap data fast
📸 gotta find 'em all; spatial reasoning benchmark for LLMs
🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
Automatic Exploit Generation with LLMs