Ouroboros

Name: Ouroboros
Author: Q00

Q00

Local agent OS for spec-first AI coding: a replayable, ledger-recorded interview, execute, evaluate and evolve loop that MCP clients can drive.

Setup

Choose your client, copy the config, then fill in any required environment variables.

claude mcp add ouroboros -- uvx ouroboros-ai

~/.codex/config.toml

[mcp_servers.ouroboros]
command = "uvx"
args = ["ouroboros-ai"]

# codex mcp add ouroboros -- uvx ouroboros-ai

~/.cursor/mcp.json

{
  "mcpServers": {
    "ouroboros": {
      "command": "uvx",
      "args": [
        "ouroboros-ai"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "ouroboros": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ouroboros-ai"
      ]
    }
  }
}

~/.gemini/settings.json

{
  "mcpServers": {
    "ouroboros": {
      "command": "uvx",
      "args": [
        "ouroboros-ai"
      ]
    }
  }
}

claude_desktop_config.json

{
  "mcpServers": {
    "ouroboros": {
      "command": "uvx",
      "args": [
        "ouroboros-ai"
      ]
    }
  }
}

.trae/mcp.json

{
  "mcpServers": {
    "ouroboros": {
      "command": "uvx",
      "args": [
        "ouroboros-ai"
      ]
    }
  }
}