claw-orchestrator

Claw Orchestrator runs several coding agents as persistent sessions behind one API and keeps the verdict out of their hands. You declare checks, the runtime runs them itself, reads the exit codes and keeps the evidence on disk.

claw-orchestrator sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward One runtime for Claude Code, Codex, Antigravity, Grok Build and OpenCode. A representative use case is Stop trusting an agent's own "all tests pass" claim. The listed license is MIT. GitHub stars are currently 596. Relevant tags include coding-agents, orchestration.