CCCC

Coordinate your coding agents like a group chat

Read receipts, delivery tracking, cross-instance collaboration, and mobile ops — for Claude Code, Codex, ChatGPT Web, and other supported runtimes in one durable group.

Run multiple coding agents as a persistent, coordinated team across runtimes, machines, and trusted working groups — not a pile of disconnected terminal sessions.

One install command. No Rust toolchain or infrastructure required.

English | 中文 | 日本語

Why CCCC

When several coding agents share work, you need to know who owns a task, whether a message reached its recipient, and what survives a restart. CCCC brings that coordination into one place, with Web and IM access when you are away from the terminal.

CCCC runs your agents as one durable, coordinated system:

• Durable coordination — message history lives in an append-only ledger; tasks and shared context have their own persistent stores.
• Visible delivery semantics — routing plus separate stored, runtime-delivery, read, and reply facts replace best-effort prompting.
• One control plane — Web UI, CLI, MCP, and IM bridges all operate on the same daemon-owned state.
• Multi-runtime by default — Claude Code, Codex CLI, ChatGPT Web, Grok Build, and other supported runtimes can collaborate in one group.
• CCCC Connect across instances — use same-account discovery, approved cross-member Group connections, or account-free Direct connections; each instance keeps its own state and access boundaries.
• Local-first operations — one install command, runtime state in CCCC_HOME, and remote supervision only when you choose to expose it.

What CCCC Does

CCCC installs with one command and needs no separately operated database, message broker, or Docker:

0.4.42 Highlights

• Optional official ACP: Antigravity, GitHub Copilot, Devin CLI and Cursor support structured Actors and Voice Analyst without a native terminal. TUI remains the default; saved mode changes apply on restart or next start.
• Voice investigations and host personas: ACP investigations show task status, decisions and results; completed call-bound work returns to that call's Realtime context. Host APIs can request persona calls without an Analyst or Actor notifications.
• Conversation recovery: Claude pauses unverifiable resumes with visible diagnostics and explicit recovery; Codex resumes long conversations without transferring their full history to CCCC. Closing a managed terminal preserves its healthy provider session.
• Clearer daily controls: thin activity rings, accurate unread Mail badges, retained per-Group recipients, installation detection and more predictable Actor/Profile saves.
• Grok and lifecycle reliability: required Bot URLs work with linked Profiles, browser login windows close independently, and Unix process cleanup retains unresolved ownership records across crashes.

See the 0.4.42 release notes for setup, upgrade steps and validation limits. When upgrading an older Actor-specific ChatGPT connector setup, follow the shared-connector migration in the 0.4.41 notes.

Quick Start

Install

# macOS / Linux (recommended)
curl -fsSL https://chesterra.github.io/cccc/install.sh | sh

# Windows CMD or PowerShell (recommended)
powershell.exe -NoProfile -ExecutionPolicy Bypass -Command "[Net.ServicePointManager]::SecurityProtocol = [Net.ServicePointManager]::SecurityProtocol -bor [Net.SecurityProtocolType]::Tls12; Invoke-RestMethod 'https://chesterra.github.io/cccc/install.ps1' | Invoke-Expression"

# Native platform wheel (pip compatibility)
python -m pip install -U "cccc-pair>=0.4.36"

CCCC uses one native Rust implementation. The website installer is recommended. The pip command installs the same native executable in a platform wheel for package-manager compatibility; it does not install a Python daemon, launcher, or fallback. Supported targets are Linux x86-64 (glibc 2.28+), Apple Silicon macOS 11+, and Windows x86-64. CCCC v0.4.37 is the final release for Intel Macs; newer releases do not publish x86_64-apple-darwin artifacts.

Upgrade

# Website-installer ownership
cccc update

# pip ownership
python -m pip install -U "cccc-pair>=0.4.36"

Use cccc update --check to query the latest channel release and inspect the installation owner and native platform requirements without changing the installation or running services. It also works for pip-owned commands. Add --offline for local details without a network request. A pip-owned command refuses standalone self-update and prints the package-manager command instead. Both channels install the same native product, but each remains owned by the installer that created it. Before a pip upgrade, run cccc daemon stop and close any foreground CCCC process so the package manager can replace the executable, especially on Windows. To switch from pip to the website installer in the same command directory, first run python -m pip uninstall cccc-pair; the standalone installer deliberately refuses to overwrite pip-owned files, even with CCCC_ALLOW_REPLACE_EXISTING=1.

If an older cccc update stays on 0.4.35, use the version-constrained pip command above in the Python environment that owns that installation. 0.4.35 was the last portable Python release; an unsupported platform can silently select it with an unconstrained pip upgrade. The minimum version makes that mismatch an explicit error. See the upgrade FAQ.

Launch

cccc

Open http://127.0.0.1:8848 — by default, CCCC brings up the daemon and the local Web UI together. Direct localhost / 127.0.0.1 use stays passwordless and does not create an Access Token. Explicit Admin Access Tokens are required only when enabling LAN, Remote Access, public URL, or reverse-proxied access.

cccc status            # product, daemon, groups, actors, and agent runtimes
cccc doctor            # installation and environment diagnostics
cccc daemon status     # explicit daemon lifecycle status

cccc python, cccc rust, and the former ccccd alias are retired. Existing automation should use cccc daemon ...; compatible daemon state filenames are retained so 0.4.35 homes can be adopted without a Python runtime.

Create a multi-agent group

Install and sign in to the agent CLIs you intend to use first. This example uses Claude Code and Codex CLI.

cd /path/to/your/repo
cccc attach .                              # bind this directory as a scope
cccc setup --runtime claude                # prepare only the runtimes used here
cccc setup --runtime codex
cccc actor add foreman --runtime claude    # first actor becomes foreman
cccc actor add implementer --runtime codex # add a peer
cccc group start                           # start all actors
cccc send "Please inspect the repo and propose the first safe task." --to foreman
cccc tracked-send "Please take the first concrete task and reply with validation evidence." \
  --to implementer \
  --title "First concrete task" \
  --outcome "The change and validation evidence are reported"

You now have two agents collaborating in a persistent group with full message history, delivery tracking, and a web dashboard. The daemon owns delivery and coordination, and runtime state stays in CCCC_HOME rather than inside your repo.

What you should see: in