Ouroboros
OPEN SOURCE · MIT

Your coding agent writes the code.
Ouroboros verifies the result.

Ouroboros manages the requirements, execution, evaluation, and records of AI coding work. It pins the spec before the run and verifies the result after it.

Claude CodeCodex CLIGitHub Copilot CLIOpenCodeHermesGeminiKiro CLIPi CLIZcodeGooseGJCAntigravity CLIGrok Build CLI

Four separate runs, four hosts. Different tasks on purpose — the engine is what is shared, not the prompt.

Terminal recording of the ouroboros CLI interview reporting an ambiguity score
Terminal CLI — a task-management CLI: ouroboros init start asking about ordering and scope, then reporting an ambiguity score
Screen recording of the ChatGPT app calling Ouroboros as an integration
ChatGPT (Codex) — called as an integration, on a video-publishing harness: the interview, its advisory lanes, and the ambiguity ledger
Screen recording of Claude Code running six Ouroboros interview advisory lanes in parallel
Claude Code — a YouTube automation task, with the six advisory lanes running in parallel before the interview submits
Screen recording of a Discord bot running the Ouroboros interview and reporting a final ambiguity of 0.15
Hermes (Discord) — a kart-racing game, run as a chat bot, ending at Final ambiguity: 0.15

Install

Run in your terminal:

zsh
claude plugin marketplace add Q00/ouroboros
claude plugin install ouroboros@ouroboros

Requires Claude Code. No Python needed. Prefer a standalone CLI? pip install ouroboros-ai — see the install guide.

How it works

Diagram: an idea passes through Ouroboros, which produces a Seed and records, while the runtime produces code and tests
The input is an idea. Ouroboros manages the work. The runtime writes the code. The output is code plus records.

Documentation