Enderfga/claw-orchestrator

Run Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-agent councils, an OpenAI-compatible endpoint, an MCP server, and an ACP agent any editor can drive.

What it solves

Coding CLIs (like Claude Code or Grok Build) are typically designed for human interaction at a terminal. Claw Orchestrator transforms these CLI-based coding agents into headless, programmable engines that can be managed via API, coordinated in groups, and integrated into larger automated workflows.

How it works

It acts as a runtime layer that wraps various coding CLIs as persistent sessions. It provides a unified interface to control multiple engines (such as Claude Code, Codex, and Antigravity) and introduces a "Durable Run Kernel" to manage complex state transitions, checkpoints, and retries. The system can be accessed via a CLI, a TypeScript API, an OpenAI-compatible proxy, or the Model Context Protocol (MCP).

Who it’s for

Developers and AI engineers who want to automate coding agents, run multi-agent consensus loops, or integrate professional coding CLIs into their own IDEs and agentic frameworks.

Highlights

  • Multi-Agent Council: Runs parallel agents in isolated git worktrees to vote on a consensus.
  • Autoloop: An autonomous three-agent loop consisting of a Planner, Coder, and Reviewer.
  • Ultraapp: A specialized workflow where a council of agents turns a brief interview into a deployed web application.
  • Verification Plane: Executes acceptance contracts (HTTP probes, screenshots, diff policies) to verify that a task is actually completed.
  • Broad Compatibility: Supports Claude Code, Codex, Antigravity, Grok Build, OpenCode, and any custom CLI subprocess.
  • Observability: Includes a durable JSONL ledger for tracking token usage, costs, and duration across different engines.

Related

  • Project
    jnMetaCode/agency-orchestrator

    Agency Orchestrator is a Node‑JS tool that lets you run dozens of AI “expert” roles together. You can write a short YAML workflow or simply give a one‑sentence prompt; AO picks the right roles, builds a DAG, calls LLM providers (Claude, DeepSeek, OpenAI, etc.), runs steps in parallel, and produces a final report. It includes a web Studio UI, role libraries (267 Chinese roles + multilingual packs), support for key‑less providers, acceptance criteria, resumable runs, and integrations with coding assistants via an MCP server.

  • Project
    qingchencloud/clawpanel

    A visual management panel for AI Agent frameworks like OpenClaw, Hermes Agent, and DeepSeek Harness, featuring a built-in AI assistant for system diagnosis and configuration.

  • Project
    OpenLAIR/dr-claw

    Dr. Claw is an open‑source, model‑agnostic AI research assistant that provides a unified UI/CLI for the whole research workflow—literature survey, idea generation, experiment code, analysis, paper drafting, and slide creation—driven by Claude Code, Gemini, Codex or any OpenRouter model.

  • Project
    Gitlawb/openclaude

    OpenClaude is an open‑source, terminal‑first CLI that lets developers interact with many LLM providers (cloud APIs, Ollama, Gemini, etc.) for coding‑assistant tasks. It offers unified provider setup, tool‑driven multi‑step workflows, background sessions, a repo‑map for code‑base awareness, a VS Code extension, and even a pixel‑art companion. Install via npm, configure providers with `/provider`, and use the REPL or background commands to generate, refactor, or debug code.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.