Stars
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
AI agent for penetration testing. Like Claude Code, but for security. Open source, MCP-native, works with any LLM.
The best-benchmarked open-source AI memory system. And it's free.
🥷 Engineering habits you already know, turned into skills Claude can run.
Turn any web app into an API. Chrome extension captures browser traffic, auto-generates schemas, lets AI replay APIs directly. No official API needed.
An agent that can help triage vulnerabilities across multiple codebases
OpenShell is the safe, private runtime for autonomous AI agents.
[ICLR 2026] Tina: Tiny Reasoning Models via LoRA
Local-first permanent, persistent memory for all agents and humans
A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench, picoCTF and more.
Fast, accurate & comprehensive text measurement & layout
Convert the cookies from Chrome's Application -> Storage -> Cookies, into the Netscape format accepted by youtube-dl
Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.
Fully automatic censorship removal for language models
OBLITERATE THE CHAINS THAT BIND YOU
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking
Fast, zero-dependency credential testing tool in Go. Brute force SSH, MySQL, PostgreSQL, Redis, MongoDB, SMB, and 20+ protocols. Hydra alternative with native nerva/naabu pipeline integration.
Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows
Recursive Language Models (https://arxiv.org/abs/2512.24601)
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Lightpanda: the headless browser designed for AI and automation
Vulnerable Target (VT) is a specialized tool designed for security professionals, researchers, and educators that creates intentionally vulnerable environments across multiple platforms.
🎃 A fast, out-of-the-box terminal built for AI coding.
Training neural networks on Apple Neural Engine via reverse-engineered private APIs