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

Agentic AI security tool that applies proactive, attacker-first analysis directly to source code.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.

Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

Pebble puts a tiny Obsidian note in your menu bar — click, write, done. 🪨

The agent that grows with you

CLI + skill for the Autoloops upskill registry. Search, inspect, report on, and publish agent skills from your shell.

The best-benchmarked open-source AI memory system. And it's free.

/:\ gitStream - Workflow automation for your git repo. Use YAML to auto-assign reviewers, auto-merge PRs, automatic PR labeler, and more.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Structured AI workflows made easy

Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

Async-first meta framework for building enterprise-grade multi-agent systems.

Plays calming elevator music for you while Claude cranks away.

Automatically injects ejson decrypted secrets into your Rails.application.credentials.

Nix, the purely functional package manager

Process manager for Procfile-based applications and tmux

Build Real-Time Knowledge Graphs for AI Agents

A GitHub Action that uses AI to generate a quiz from your pull request

A starter MCP server in Python.

A self-contained game that fits inside a QR code inspired by DOOM 1993 and The Backrooms

Typed interactions with the GitHub API v3

GitHub Action to prompt GitHub Models about... well, anything!

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Learn to code securely while having fun through our popular open source in-editor experience, designed for developers, students, and anyone curious about security. Get started for free in under 2 m…

Gather metrics on issues/prs/discussions such as time to first response, count of issues opened, closed, etc.

Python program that uses OpenCV to detect and identify playing cards from a PiCamera video feed on a Raspberry Pi