Enderfga/claw-orchestrator

What it solves

Coding CLIs (like Claude Code or Grok Build) are typically designed for human interaction at a terminal. Claw Orchestrator transforms these CLI-based coding agents into headless, programmable engines that can be managed via API, coordinated in groups, and integrated into larger automated workflows.

How it works

It acts as a runtime layer that wraps various coding CLIs as persistent sessions. It provides a unified interface to control multiple engines (such as Claude Code, Codex, and Antigravity) and introduces a "Durable Run Kernel" to manage complex state transitions, checkpoints, and retries. The system can be accessed via a CLI, a TypeScript API, an OpenAI-compatible proxy, or the Model Context Protocol (MCP).

Who it’s for

Developers and AI engineers who want to automate coding agents, run multi-agent consensus loops, or integrate professional coding CLIs into their own IDEs and agentic frameworks.

Highlights

• Multi-Agent Council: Runs parallel agents in isolated git worktrees to vote on a consensus.
• Autoloop: An autonomous three-agent loop consisting of a Planner, Coder, and Reviewer.
• Ultraapp: A specialized workflow where a council of agents turns a brief interview into a deployed web application.
• Verification Plane: Executes acceptance contracts (HTTP probes, screenshots, diff policies) to verify that a task is actually completed.
• Broad Compatibility: Supports Claude Code, Codex, Antigravity, Grok Build, OpenCode, and any custom CLI subprocess.
• Observability: Includes a durable JSONL ledger for tracking token usage, costs, and duration across different engines.