Claw Orchestrator — run Claude Code, Codex, Gemini, Cursor Agent, OpenCode and custom coding CLIs as one unified runtime. Drop into Hermes Agent, Claude Desktop, Cursor, Cline, Continue, Zed, Windsurf, Goose or any Model Context Protocol (MCP) host, install as an OpenClaw…
$git clone https://github.com/enderfga/claw-orchestratorInstalls into the current project.
Install claw-orchestrator by running `git clone https://github.com/enderfga/claw-orchestrator`, then use it for the current task and follow its documentation at https://github.com/enderfga/claw-orchestrator.
| 1 | <p align="center"> |
| 2 | <img src="./assets/banner.jpg" alt="Claw Orchestrator" width="100%"> |
| 3 | </p> |
| 4 | |
| 5 | # Claw Orchestrator |
| 6 | |
| 7 | > A runtime for coding agents. Wrap Claude Code, Codex, Antigravity, Cursor Agent, OpenCode, or any custom CLI as persistent programmable sessions; coordinate them in multi-agent councils; run autonomous Planner / Coder / Reviewer loops; or hand a five-question interview to an Opus council that ships a deployed web app at `localhost:19000/forge/<slug>/`. |
| 8 | |
| 9 | [](https://www.npmjs.com/package/@enderfga/claw-orchestrator) |
| 10 | [](https://github.com/Enderfga/claw-orchestrator/actions/workflows/ci.yml) |
| 11 | [](https://opensource.org/licenses/MIT) |
| 12 | |
| 13 | Coding CLIs are designed for humans at terminals. Claw Orchestrator turns them into headless engines and stacks an agent platform on top: a 65-tool API that scales from a single session call up to a fully generated, deployed web app — reachable through the CLI, the OpenClaw gateway, the Model Context Protocol, or directly from TypeScript, and visible through an embedded three-tab dashboard. |
| 14 | |
| 15 | |
| 16 | |
| 17 | https://github.com/user-attachments/assets/fbd2b0ea-28d8-4387-9894-c29cf15ba030 |
| 18 | |
| 19 | <p align="center"> |
| 20 | <sub><b>Control · Council · Autoloop · Ultraapp</b> — the four movements in 35s</sub> |
| 21 | </p> |
| 22 | |
| 23 | --- |
| 24 | |
| 25 | ## Features |
| 26 | |
| 27 | | Capability | What it does | Reference | |
| 28 | | --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------- | |
| 29 | | **Persistent Sessions** | Long-lived coding agents kept alive across requests, with full context, tool, model, and worktree control. | [`sessions.md`](./skills/references/sessions.md) | |
| 30 | | **Multi-Engine Runtime** | One interface over Claude Code, Codex, Antigravity (agy), Cursor Agent, OpenCode, and arbitrary custom CLIs. | [`multi-engine.md`](./skills/references/multi-engine.md) | |
| 31 | | **Multi-Agent Council** | Parallel agents in isolated git worktrees, voting on consensus until they agree. | [`council.md`](./skills/references/council.md) | |
| 32 | | **Fan-out** | Run one task across N engine/model agents in parallel and collect their answers, with an optional synthesis pass — the cross-engine best-of-N / diverse-perspective primitive (no rounds or worktrees). | [`tools.md`](./skills/references/tools.md) | |
| 33 | | **ultracode** | `session_start({ ultracode: true })` lets Claude orchestrate a dynamic JS workflow and fan out to subagents per task (Claude engine). | [`tools.md`](./skills/references/tools.md) | |
| 34 | | **Autoloop** | Three-agent autonomous workspace iteration with independent engine/model selection for Planner, Coder, and Reviewer. Chat with the Planner; it spawns Coder + Reviewer into a self-iterating subloop and pushes you on regression, targ |