https://github.com/user-attachments/assets/5bf9bea8-e5ac-4632-a292-a80a45831dff
News
- [2026-10] , an autonomous agent that profiles, optimizes and validates AI training code, now runs its goal mode on Claw Orchestrator.
에이전트 강화
게시자의 자체 명령입니다. PlugMCP 엔드포인트가 아닙니다.
Host a copy with our keys and logs.
npx -y @enderfga/[email protected]Claude Code에는 로컬 명령용 설치 링크가 없습니다. 아래 명령을 복사해 터미널에서 실행합니다.
claude mcp add enderfga-claw-orchestrator-github -- npx -y @enderfga/claw-orchestrator@7.23.4터미널에서 실행합니다.
{ "mcpServers": { "enderfga-claw-orchestrator-github": { "command": "npx", "args": [ "-y", "@enderfga/[email protected]" ] } }}claude_desktop_config.json
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행게시자 제공
https://github.com/user-attachments/assets/5bf9bea8-e5ac-4632-a292-a80a45831dff
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.
engine: 'acp'), with presets for
Kimi Code and dsh.clawo goal keeps a Codex /goal running for hours on one thread, reattaches it after a
crash, and judges the result with your checks.verified, refuted or unverified, and editing the tests its contract
runs refutes it (guide).clawo fanout asks several at once; session_handoff moves a live conversation to another engine in the same
workspace (guide).clawo goal runs a Codex /goal unattended on one thread, resumes it after usage limits within a
bound, optionally inside your own sandbox (guide).clawo runs) and a maxBudgetUsd cap the runtime enforces on
every engine (guide).claude-squad, Conductor and Vibe Kanban are interfaces for running agents side by side in worktrees; Claude Code subagents and Codex's parallel attempts stay within one vendor. Claw Orchestrator is a headless runtime underneath: several vendors behind one API, durable workflows, and a verification step the agents cannot edit. They can be used together.
Requires Node 22+ and at least one engine CLI installed and logged in (claude, codex, agy, grok or opencode).
npm install -g @enderfga/claw-orchestrator
clawo serve & # local runtime + dashboard on 127.0.0.1:18796
clawo solve "The test fails. Fix price.js." --engine codex \
--check "npm test" --check "node ../holdout/price.spec.mjs" --wait
clawo verify <runId> # each check, why it failed, the files that changed
clawo runs --since 1h # every turn on every engine: model, tokens, cost, verdict
clawo fanout "How would you speed up this test suite?" --engines claude,codex,grok --synthesize --wait
clawo goal --objective-file GOAL.md --check "npm run bench:check" --check-timeout 120 --wait
The server writes an access token to ~/.openclaw/server-token and the CLI reads it from there. To sign in the
browser once, open http://127.0.0.1:18796/login?token=<token>&redirect=/dash.
import { SessionManager } from '@enderfga/claw-orchestrator';
const manager = new SessionManager();
await manager.startSession({ name: 'fix-tests', engine: 'claude', cwd: '/project' });
const result = await manager.sendMessage('fix-tests', 'Fix the failing tests');
From an MCP host, ask for workflow_start with template solve, a task, and a contract such as
{"checks":[{"type":"command","cmd":"npm","args":["test"]}]}. In an ACP editor, the model selector is grouped by
engine, so one dropdown switches between Claude, Codex, Antigravity and Grok models mid-session.
An agent that serves the Agent Client Protocol on stdio runs as
engine: 'acp'; any other coding CLI that runs as a
subprocess can be wired up as a custom engine.
The versions above are what the weekly sweep last ran. scripts/sweep.ts measures each core engine's installed,
pinned and upstream version, diffs the flags the wrapper passes against the binary's --help, runs one live turn
through the real wrapper class, smokes the ACP and MCP entry points, and checks src/models.ts against the
OpenAI, Anthropic and xAI published price tables. It contains no model call, so the check that reports a wrapper as broken does not
share the wrapper's failure modes.
scripts/sweep-workflow.json wraps the same script as a durable run on this project's own kernel: verifier → router
→ an agent that drafts the alignment on a sweep/<date> branch → a human gate. A person reviews and merges; the
orchestrator does not edit its own code unattended.
clawo goal
(blog).Using Claw Orchestrator in a project or paper? Open a pull request to add it here.
If Claw Orchestrator helps your research, please cite it:
@misc{fang2026claworchestrator,
title = {Claw Orchestrator: A Unified Runtime for Coding Agent CLIs},
author = {Fang, Guian},
year = {2026},
howpublished = {\url{https://github.com/Enderfga/claw-orchestrator}}
}
Research built on Claw Orchestrator:
@misc{researchboost2026infra,
author = {{ResearchBoost Team}},
title = {{ResearchBoost}: {RSI} starts with Infra},
year = {2026},
url = {https://ydove0324.github.io/hx_resume/blog/researchboost/}
}
@inproceedings{fang2026declare,
title = {Declare, Compile, Look: Coordinate-Free Layout Generation with Vision-in-the-Loop Repair},
author = {Fang, Guian and Liu, Mengsha and Shou, Mike Zheng},
booktitle = {ECCV 2026 Multimodal Digital Agents Workshop},
year = {2026},
url = {https://openreview.net/forum?id=Romd50Ce0w}
}
See CONTRIBUTING.md. Run npm run build && npm run lint && npm run format:check && npm run test
before submitting.
MIT, see LICENSE.
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend
{ "mcpServers": { "enderfga-claw-orchestrator-github": { "command": "npx", "args": [ "-y", "@enderfga/[email protected]" ] } }}개요
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.
도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
Claw Orchestrator은(는) stdio를 통해 로컬에서 실행됩니다.
마지막 확인: 2026-10-27. Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.