ChesterRa/cccc

Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your phone. One pip install, zero infrastructure. A production‑minded orchestrator for 24/7 workflow

What it solves

CCCC coordinates multiple coding agents from different runtimes (such as Claude Code, Codex, and ChatGPT Web) into a single, durable team. It eliminates the problem of disconnected terminal sessions by providing a unified control plane with persistent message history, delivery tracking, and cross-instance collaboration.

How it works

CCCC uses a central daemon that manages an append-only ledger of all collaboration events and messages. This daemon acts as the single writer for the state, which is then exposed via a Web UI, CLI, and MCP tools. It supports a wide variety of agent runtimes by integrating them as "Actors" within a Group, allowing them to communicate via routing (e.g., @all, @foreman) and share a workspace. It can also bridge to IM platforms like Telegram, Slack, and Discord for remote supervision.

Who it’s for

Developers who use multiple AI coding agents and need a way to orchestrate them as a coordinated team rather than individual tools, as well as teams who want to share agent coordination across different machines or accounts.

Highlights

  • Multi-runtime support: Integrates 19+ built-in runtimes including Claude Code, GitHub Copilot, Devin, and Grok.
  • Durable coordination: Uses an append-only ledger for message history and persistent stores for tasks and context.
  • Reliable messaging: Implements explicit delivery, read, and reply tracking instead of best-effort prompting.
  • Unified control plane: Provides a Web UI, CLI, and IM bridges all operating on the same daemon-owned state.
  • Local-first: Runtime state is stored in CCCC_HOME rather than the project repository.
  • CCCC Connect: Enables collaboration between different CCCC instances via account-based discovery or direct group pairing.

Related

  • Project
    CronusL-1141/AI-company

    AI Team OS is a local, shared operating layer for Claude Code and Codex that persists tasks, memory, reports, and team communication across sessions. It lets multiple AI agent sessions coordinate on the same project without losing context, while keeping each host's native tools and permissions.

  • Project
    firstintent/ccteam

    ccteam is a Rust‑based daemon that lets you run multiple coding‑assistant LLMs (Claude Code, Codex, Grok, Kimi, DeepSeek Harness, Pi) as a coordinated team, with a single console (Telegram/Slack/web), cost ledger, and programmable flows.

  • Project
    spacering-net/codeg

    A multi-agent coding workspace that integrates various AI coding agents into a single visual interface, allowing them to collaborate and work on the same project.

  • Project
    zts212653/clowder-ai

    Clowder AI is a platform layer that turns isolated AI coding agents into a collaborative team, giving them persistent identities, shared memory, cross-model review, and agent-to-agent messaging so you don't have to manually route copy-paste context.

  • Project
    multica-ai/multica

    Multica is a self‑hostable (or cloud) platform that lets you treat LLM‑based coding agents (Claude Code, Codex, Cursor, etc.) as teammates on a Kanban board. Agents run on a runtime you control, keep context, log every step, and hand back pull requests for human review. The stack includes a Next.js web UI, Go backend, PostgreSQL, and an agent daemon that spawns any supported CLI. It offers cost analytics, review gates, Slack/Telegram integrations, and a full CLI/API for automation. Licensed under a custom Apache‑2.0‑style license.