openclaw-orchestrator and claw-orchestrator
About openclaw-orchestrator
zeynepyorulmaz/openclaw-orchestrator
Adaptive multi-agent orchestration framework — break down complex goals into parallel tasks, route them to specialized LLM agents, and iterate with a real-time web dashboard. TypeScript, Zod-validated, SQLite-backed.
Implements a capability-based routing system where agents are sandbox-isolated by role and tool access (researcher with search vs. coder with bash), reducing security risk through least privilege. Uses an adaptive feedback loop where an LLM planner orchestrates specialized agents in parallel steps, re-evaluating accumulated results and deciding whether to route to researcher/coder/analyst agents or finish—no rigid DAG required. Supports OpenClaw gateways, HTTP endpoints, or plain async functions as agent adapters, with a real-time dashboard using Server-Sent Events and SQLite for step history.
About claw-orchestrator
laozuzhen/claw-orchestrator
Claw Orchestrator
Scores updated daily from GitHub, PyPI, and npm data. How scores work