Basic multi-purpose LLM Agent in the style of Norton-Commander

meat.dev

Local AI powered red teamer on a phone

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

idac - IDA Pro command line tool for agents and humans

SOTA Open Source TTS

Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

Per-entry-point, navigable call-graph visualizations of Solidity repositories — for Web3 security auditors.

🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering

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

A new open-source format for interactive video on the web, with a built-in state machine, frame-accurate transitions, and packed-alpha transparency.

Make non-self-contained C/C++ headers parse cleanly under clangd in VS Code by injecting a synthetic preamble from a recently-seen includer TU.

Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting

This does for Documents what repo-browser does for repos. A local AI powered Document search engine

Stealth Chromium engine that stops scrapers and browser agents from getting blocked, with one line of code change.

An extensions for Hypothesis that provides fully automatic testing for type hinted functions

Claudoro: Feature rich Pomodoro timer embedded into Claude Code

Implementation of the Google Zero-Knowledge library for Identity Protocols.

safer-dependencies is a security layer for Claude Code that audits packages before they’re added to your project. It detects and fixes risky dependencies, including CVEs, typosquats, abandoned pack…

A single archive of public exploit PoCs and vulnerability research writeups. At the time I post these, none have been reported. Feel free to report them yourself and take credit for the CVE if hand…

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

Inline proxy for software package registries to provide observability and policy controls to installs.

Fil-C: completely compatible memory safety for C and C++

GetSuperpower packages a whole AI-agent workflow as one callable skill.

Security through scrutiny

an llmwiki app

A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.