ouroboros
Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot,
Ouroboros is an MCP server and Agent OS that transforms vague ideas into verified codebases through a structured specification-first workflow. It conducts Socratic interviews to expose hidden assumptions, generates immutable seed specifications with ambiguity scoring, and implements a three-stage automated evaluation gate (Mechanical → Semantic → Multi-Model Consensus). The system supports 13 AI coding runtimes including Claude Code, Codex CLI, GitHub Copilot CLI, OpenCode, Gemini CLI, Kiro, and others, providing replayable execution contracts across different LLM backends.
Key Features
Use Cases
- 01Converting vague project ideas into complete technical specifications before coding
- 02Preventing architecture drift through immutable specification locking
- 03Automating verification of AI-generated code with multi-model consensus
- 04Running persistent evolutionary loops across session boundaries until convergence
- 05Managing brownfield repository analysis and context-aware development
- 06Publishing specifications as GitHub Epic/Task issues for team workflows
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
ouroboros — FAQ
What is Ouroboros?+
Ouroboros is an MCP server and Agent OS that implements a specification-first AI coding workflow. It turns vague ideas into verified codebases through Socratic interviews, immutable seed specifications, and automated three-stage evaluation gates across 13+ AI coding assistants.
How do I install Ouroboros?+
Install via the one-command script (macOS/Linux/WSL: curl install.sh | bash; Windows PowerShell: irm install.ps1 | iex) or manually with pip/pipx/uv ('pip install ouroboros-ai[mcp,tui]'). Then run 'ooo setup' inside your AI coding agent or 'ouroboros setup --runtime <name>' from terminal to configure your runtime.
Which AI clients and runtimes does Ouroboros work with?+
Ouroboros supports Claude Code, Codex CLI, GitHub Copilot CLI, OpenCode, Hermes, Gemini CLI, Kiro CLI, Goose, Pi CLI, OMP CLI, Zcode, GJC, Antigravity CLI, and Grok Build CLI. It also supports DeepSeek via the dsh backend or as a native plugin in DeepSeek Harness.
What are the prerequisites for using Ouroboros?+
Python 3.12+ is required (3.12-3.13 for LiteLLM profiles). You need at least one supported AI coding runtime installed. No API keys are required for the core workflow, though specific runtimes may need their own authentication (e.g., GitHub auth for Copilot CLI).
Is Ouroboros free to use?+
Yes, Ouroboros is MIT-licensed open source and free to use. The Mechanical evaluation stage is free; Semantic and Multi-Model Consensus stages use your configured LLM provider and incur their standard costs.
What is the ambiguity score and why does it matter?+
The ambiguity score quantifies specification clarity (1 - weighted clarity across goal/constraints/success criteria). A score ≤0.2 is required to generate seed specifications; higher scores block code generation unless you explicitly use 'force', ensuring assumptions are clarified before building.
How do I install ouroboros?+
Open the source repository on GitHub and follow its README. ouroboros is a mcp server — MCP Agents Market links you directly to the official repo.
Is ouroboros free?+
ouroboros is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.