Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONAn unofficial Codex Skill for repository delivery: it routes work between the current task, internal agents and optional App tasks, with explicit ownership, isolated Git worktrees, independent review, an installer with check/dry-run modes, and deterministic tests.
oh-my-claudecode is a multi-agent orchestration layer for Claude Code, offering team pipelines, tmux CLI workers for Codex/Gemini/Cursor, autopilot and verify loops, plus reusable skill extraction.
VALP is an open protocol and reference CLI for visible, evidence-backed multi-agent work. It audits agent completion claims by checking receipts, expected evidence, review gates, and final synthesis to prevent false-done states.
Agent Interlock is an agentic AI security framework that declares the actors and trust boundaries of an AI agent system, wraps each actor's tools through an SDK or proxy, and enforces MCP tool threats M1–M9 across observe, shadow and enforce stages, recording every verdict in an append-only ledger.
HEE is a doctrine-first execution framework that coordinates human reasoning, machine assistance, and automation through deterministic typed YAML objects with hash-derived identities, verification checks, and GPG signature chains.
Ruflo is an agent meta-harness for Claude Code and Codex that enables multi-agent swarms, self-learning memory, RAG integration, federation, and extensive plugin ecosystem to build coordinated AI workflows.
