marian2js / opengoat
Build organizations of OpenClaw agents that coordinate work across Codex, Claude Code, Cursor, OpenCode, and more š š š
View on GitHubAI Architecture Analysis
This repository is indexed by RepoMind. By analyzing marian2js/opengoat in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Repository Overview (README excerpt)
Crawler viewOpenGoat Build AI Autonomous Organizations of OpenClaw Agents. = 20.11" /> **OpenGoat** allows you to build herarchical organizations of AI agents that coordinate work across multiple tools, including Claude Code, Codex, Cursor, GitHub Copilot CLI, Lovable, and more. --- Installation That's it. Open and start messaging Goat, your AI co-founder. Alternative: Docker Then open . From Source (without global npm install) Documentation (Mintlify) Use before publishing documentation changes. When agents execute commands from their OpenGoat workspace, use the workspace shim: CLI Quick Start (Optional) Runtime: Node . Run the production UI server from the CLI: Restart a running UI server: Use an external OpenClaw gateway: Typical Workflows Create a project CMO This provisions a project-scoped CMO agent workspace at , installs the skill by default, and bootstraps the CMO with an internal first-run prompt sequence derived from the project URL. Build the organization Run role-based work Configure the default entry agent You can also set directly in . Keep session continuity Operate with tasks Skills Role skill behavior: ⢠OpenClaw agents use role-specific board skills: ⢠managers: ⢠individuals: ⢠Non-OpenClaw agents use one board skill: License MIT