Claw Orchestrator
Turns Claude Code, Codex, Antigravity and other coding CLIs into programmable, persistent engines you can orchestrate in sessions, councils and autonomous loops.
- Source repo
- Enderfga/claw-orchestrator
- Stars
- ★ 580
- Last updated
- 1d ago
- License
- MIT
- Primary language
- TypeScript
- FA score
- 54/100 · Major gaps
At a glance
- Works with
- Universal · cross-platformCodex · Claude Code · OpenAI API · Claude API
- You'll need
- Typical use
- Developers who need to drive Claude Code or Codex headlessly from scripts or backend services with full context retained across requests.
- Main limitation
- Hard dependency on underlying coding CLIs: you must install and maintain claude, codex, agy, grok or opencode, with tested version requirements (e.g. claude 2.1.260, codex 0.153.2).
- Source review
- 54/100 · Major gaps
What does this agent do, and when should you use it?
Claw Orchestrator is a runtime for coding agents that wraps human-facing coding CLIs — Claude Code, Codex, Antigravity, Grok Build, OpenCode, or any custom CLI — as persistent, programmable sessions. It exposes a 77-tool API that scales from a single session call to a fully generated, deployed web app, reachable via the CLI, the OpenClaw gateway, an MCP server, an ACP agent, or TypeScript, with a three-tab embedded dashboard for visibility. Core primitives include multi-agent councils (parallel agents in isolated git worktrees voting to consensus), a Planner/Coder/Reviewer Autoloop, cross-engine fan-out, and Ultraapp, which turns a five-question interview into a deployed web app. A durable run kernel organizes declarative workflows over agent/fanout/council/verifier/human_gate nodes with checkpointed state transitions that survive process restarts. Every turn is appended to a durable JSONL run ledger recording engine, model, tokens, cost and duration, and the runtime enforces maxBudgetUsd spend caps across all engines.
After installing, clawo serve starts a dashboard and HTTP server at 127.0.0.1:18796/dash. You create named persistent sessions via the SessionManager class or CLI (clawo session-start / session-send), specifying engine, model, cwd and worktree. The council capability runs parallel agents in isolated git worktrees and votes until consensus; fanout distributes one task across N engine/model agents with an optional synthesis pass; ultracode lets Claude orchestrate a dynamic JS workflow fanning out to subagents per task. Autoloop runs Planner, Coder and Reviewer as a self-iterating subloop; Ultraapp uses a three-agent Opus council to turn a five-question interview into a Tailwind web app deployed at localhost:19000/forge/<slug>/. The verification plane executes acceptance contracts (commands, HTTP probes, screenshots, diff policy, file assertions) producing an on-disk evidence bundle — runs with a contract cannot reach completed unless they pass, and runs without one complete as unverified. POST /v1/chat/completions provides an OpenAI-compatible proxy; clawo-mcp exposes an MCP server; clawo acp lets editors drive it as their coding agent over Agent Client Protocol.
- Developers who need to drive Claude Code or Codex headlessly from scripts or backend services with full context retained across requests.
- Engineers wanting cross-model validation of a single solution: use council or fanout to run multiple engines in parallel in isolated worktrees and take consensus or best-of-N.
- Teams who want an autonomous loop continuously iterating a codebase: chat with the Planner while Coder and Reviewer loop, surfacing regressions, target hits and decision points.
- Users integrating coding agents into MCP hosts (Claude Desktop, Cursor, Zed, Cline) or driving it from Zed, JetBrains, Neovim or Emacs via ACP.
- Projects on the OpenAI SDK that want to transparently switch underlying Anthropic/OpenAI/Google models by pointing at /v1/chat/completions without changing call sites.
- Teams needing auditable spend: query per-turn tokens, cost and attribution with clawo runs and set hard maxBudgetUsd caps.
How do you install or deploy this agent?
Prerequisites: a Node.js/npm environment and at least one supported coding CLI (claude, codex, agy, grok, opencode) or any custom CLI runnable as a subprocess. Install globally: npm install -g @enderfga/claw-orchestrator. This puts clawo-mcp on PATH. The OpenClaw plugin installs via curl -fsSL https://raw.githubusercontent.com/Enderfga/claw-orchestrator/main/install.sh | bash, which registers the plugin in ~/.openclaw/openclaw. and restarts the gateway.
How do you use this agent?
Start the server: clawo serve, dashboard at http://127.0.0.1:18796/dash. CLI sessions: clawo session-start fix-tests --engine claude --cwd . then clawo session-send fix-tests "Fix the failing tests". TypeScript: import { SessionManager } from '@enderfga/claw-orchestrator'; await manager.startSession({ name: 'fix-tests', engine: 'claude', cwd: '/project' }); then manager.sendMessage('fix-tests', '...'). Other entry points: clawo acp (or clawo-acp) to be driven by editors over ACP; register clawo-mcp with any MCP host; OpenAI-compatible endpoint at POST /v1/chat/completions.
What are this agent's strengths and limitations?
- A genuine multi-engine runtime: one interface over Claude Code, Codex, Antigravity, Grok Build, OpenCode and arbitrary custom CLIs, with mid-session engine switching.
- Durable run kernel with checkpointing: declarative workflows over verifier, human_gate, router and other nodes resume at node boundaries after process restarts, with retry, timeout, cancel and steer built in.
- Runtime-enforced verification and spend caps: contract-carrying runs cannot reach completed without passing, and maxBudgetUsd holds on Codex, Grok, agy and OpenCode too, not just Claude Code.
- Four integration surfaces (CLI, OpenClaw plugin, MCP, ACP) cover terminal-to-editor call paths, backed by a three-tab live dashboard.
- Hard dependency on underlying coding CLIs: you must install and maintain claude, codex, agy, grok or opencode, with tested version requirements (e.g. claude 2.1.260, codex 0.153.2).
- Cost scales with the multi-agent design: council, fanout and Autoloop invoke multiple engines concurrently, which can be expensive without budget configuration.
- Ultraapp's deployment boundary is local (localhost:19000/forge/<slug>/), aimed at local demos rather than production hosting.
- The editor ACP integration has documented cancellation and permission limitations; read acp.md to understand the boundaries before adopting.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|
| Claw Orchestrator This agent | 54 · Major gaps | ★ 580 | 1d ago | TypeScript | Codex · Claude Code · OpenAI API · Claude API |
| TAKT Workflow Orchestrator | 57 · Major gaps | ★ 1.4k | 5d ago | TypeScript | Codex · Claude Code · OpenAI API · Claude API |
| fx Coding Agent | 63 · Some gaps | ★ 3.1k | 4d ago | Zig | ChatGPT · Codex · OpenAI API |
| Oh My Pi | 54 · Major gaps | ★ 33k | today | TypeScript | Codex · OpenAI API · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence comprises only README, LICENSE, package., and CI configs; no implementation source. Positives: MCP tool allowlist (CLAWO_MCP_TOOLS), runtime-enforced maxBudgetUsd, acceptance contracts blocking unverified runs from 'completed', human merge gate in the sweep workflow. Deducted: no code demonstrates least privilege or confirmation behavior; a curl | bash installer is recommended, a high-risk pattern; BYOK and cookie auth are only mentioned; external effects (deploying apps to local ports, rewriting openclaw., restarting the gateway) are described with no permission-boundary detail.
Positives: engine versions maintained by a measured weekly sweep, CI covering Node 22/24 with a 15-minute hang timeout, OIDC trusted publishing pinned to npm 11.x with a documented failure lesson. Deducted: README and package. contradict each other on engine coverage (description names Gemini and Cursor Agent; the table lists Antigravity and Grok Build), hurting self-consistency; no source code evidences failure messaging, only the verified/unverified concept.
Positives: broad audience coverage (MCP/ACP/OpenClaw hosts, standalone CLI, TypeScript), capability boundaries supported by acceptance contracts, spend caps, and human gates, explicit environment requirements (Node>=22, tested engine versions). Deducted: no evidence on trigger precision; the referenced docs (mcp.md, acp.md, etc.) are absent from the evidence, so many claims are taken on trust.
Positives: clear doc architecture, complete install steps, consistent clawo/clawo-mcp/clawo-acp naming, a full MIT license consistent with package., and concrete maintenance mechanics (weekly sweep, CONTRIBUTING, CI). Deducted: version 7.1.1 with no CHANGELOG file, so update history is untraceable; the referenced docs themselves are not in evidence.
Positives: unified multi-engine runtime, councils, fan-out, a durable run kernel, and a verification plane constitute real differentiated value; a JSONL run ledger separates engine self-reports from runtime measurement, making cost queryable. Deducted: all of this is asserted — no source, tests, or run evidence shows the 77 tools and four movements actually work; only 7 direct dependencies, but cost/benefit cannot be independently verified.
Positives: the README deliberately separates claims from measurement (a sweep script 'with no LLM in it', ledger ok vs verified kept apart, the human gate as 'the loop measures, proposes and verifies; a person merges'). Deducted: all key capability claims point to docs under skills/references/ that were not provided, so traceability fails; apart from package. and CI, there is almost no second source to corroborate the README's core claims.
- The recommended `curl -fsSL ... | bash` installer executes a remote script with user privileges without review; prefer npm installation and audit the script first.
- This review contains no implementation source or referenced docs; all core capabilities (77 tools, councils, ultraapp) are README assertions, unverified by static code inspection and never executed.
- Publisher identity is unverified (npm: @enderfga); assess supply-chain trust yourself and verify package integrity and provenance before installing.
- The product drives multiple coding agents with real side effects on local files, git worktrees, and local port deployments; constrain its filesystem and network permissions in an isolated environment before use.
- README and package. disagree on the supported engine list; verify actual coverage by running it yourself.