ouroboros

<strong>English</strong> | <a href="./README.ko.md">한국어</a> | <a href="./README.zh-CN.md">简体中文</a>

<br/> ◯ ─────────── ◯ <br/><br/> <br/><br/> <strong>O U R O B O R O S</strong> <br/><br/> ◯ ─────────── ◯ <br/>

<strong>It gets smarter on its own. We just hold the line.</strong> <br/> _{Skip the prompt engineering. The agent runs, fails, and gets smarter every generation. The grading command and expected result never make it into the success contract we hand it.} <br/> _{The <strong>Agent OS</strong> for replayable AI coding workflows}

<a href="#quick-start">Quick Start</a> · <a href="#why-ouroboros">Why</a> · <a href="#what-you-get">Results</a> · <a href="#the-loop">How It Works</a> · <a href="#commands">Commands</a> · <a href="#from-wonder-to-ontology">Philosophy</a> · <a href="https://ouroboros.page/learn/en/">Guide</a>

# macOS / Linux / WSL 2
curl -fsSL https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.sh | OUROBOROS_INSTALL_REF=readme-hero bash

# Windows (PowerShell) — no Python needed; installs Git and uv for you
irm https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.ps1 | iex

<p align="center">_{One command installs it. Then run <code>ooo setup</code> once inside your coding agent — details in <a href="#quick-start">Quick Start</a>.}</p> <p align="center">_{<b>Separate runs, separate hosts. Different tasks on purpose — the engine is what is shared, not the prompt</b>}</p> <td align="center" width="50%"><img src="./docs/images/ooo-interview.gif" alt="Terminal recording of the ouroboros CLI interview reporting an ambiguity score"><br>_{<b>Terminal CLI</b> — a task-management CLI: <code>ouroboros init start</code> asking about ordering and scope, then reporting an ambiguity score}</td> <td align="center" width="50%"><img src="./docs/images/host-codex.gif" alt="Screen recording of the ChatGPT app calling Ouroboros as an integration"><br>_{<b>ChatGPT (Codex)</b> — called as an integration, on a video-publishing harness: the interview, its advisory lanes, and the ambiguity ledger}</td> <td align="center" width="50%"><img src="./docs/images/host-claude.gif" alt="Screen recording of Claude Code running six Ouroboros interview advisory lanes in parallel"><br>_{<b>Claude Code</b> — a YouTube automation task, with the six advisory lanes running in parallel before the interview submits}</td> <td align="center" width="50%"><img src="./docs/images/host-hermes.gif" alt="Screen recording of a Discord bot running the Ouroboros interview and reporting a final ambiguity of 0.15"><br>_{<b>Hermes (Discord)</b> — a kart-racing game, run as a chat bot, ending at <code>Final ambiguity: 0.15</code>}</td> <td align="center" width="50%"><img src="./docs/images/host-dsh.gif" alt="Screen recording of DeepSeek Harness calling the Ouroboros interview tool and submitting advisory fan-out results"><br>_{<b>DeepSeek Harness</b> — an OSS-trend outreach script, driven from a dsh chat: <code>mcp__ouroboros__ouroboros_interview</code> turn by turn, fan-out results submitted between rounds}</td> <td align="center" width="50%"><img src="./docs/images/host-kiro.gif" alt="10x screen recording of Kiro CLI running an Ouroboros interview"><br>_{<b>Kiro</b> — the Kiro CLI running the Ouroboros interview flow, turning a vague request into a structured, testable Seed}</td> <td align="ce

…