---

Why CCCC

Using multiple coding agents today usually means lost context in terminal scrollback, no distinction between a stored message, runtime handoff, Inbox consumption, and a reply, start/stop/recover operations scattered across tools, and no way to check on a long-running group from your phone. That's why most multi-agent setups stay fragile demos instead of reliable workflows.

CCCC runs your agents as one durable, coordinated system:

• Durable coordination — working state lives in an append-only ledger, not in terminal scrollback.
• 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 the rest of the first-class runtimes can collaborate in one group.
• Group Bridge for remote teams — trusted CCCC groups can exchange explicit messages and, when granted, inspect or work with each other's local resources.
• 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 database, message broker, or Docker. Yet it gives you the pieces fragile multi-agent setups usually lack:

Capability	How
Single source of truth	Append-only ledger (ledger.jsonl) records every message and event — replayable, auditable, never lost
Reliable messaging	Send / Send + Reply / Mail, separate delivery/read/reply facts, and a Mail-only Inbox consumed in ledger order — runtime handoff never pretends a message was read
Unified control plane	Web UI, CLI, MCP tools, and IM bridges all talk to one daemon — no state fragmentation
Multi-runtime orchestration	Claude Code, Codex CLI, GitHub Copilot CLI, Cursor CLI, Devin CLI, Kiro CLI, Kilo Code CLI, Antigravity CLI, Grok Build, OpenCode, ChatGPT Web, and 5 more first-class runtimes, plus custom for everything else
Group Bridge	Connect trusted remote groups across machines or teams, starting with explicit messages and optionally granting read/full local access
Role-based coordination	Foreman + peer model with permission boundaries and recipient routing (@all, @peers, @foreman)
Local-first runtime state	Runtime data stays in CCCC_HOME, not your repo, while Web Access and IM bridges cover remote operations

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 0.4.36 has one product implementation: Rust. 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, Reach, 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

cd /path/to/your/repo
cccc attach .                              # bind this directory as a scope
cccc setup                                 # configure all available runtimes (or select one with --runtime)
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 the Web UI at http://127.0.0.1:8848, both actors show as running, the foreman's reply arrives in Chat, and the tracked request displays its delivery and read state on the message. If an actor stays stopped, run cccc doctor to check the runtime, and see the FAQ for common first-run fixes.

Programmatic Access (SDK)

Use the official SDK when you need to integrate CCCC into external applications or services:

pip install -U cccc-sdk
npm install cccc-sdk
cargo add cccc-sdk

The SDK does not include a daemon. It connects to a running cccc core instance.

Architecture

graph TB
    subgraph Agents["Agent Runtimes"]
        direction LR
        A1["Claude Code"]
        A2["Codex CLI"]
        A3["ChatGPT Web<br/>GPT-5.x via MCP"]
        A4["Grok Build"]
        A5["+ 12 more + custom"]
    end

    subgraph Daemon["CCCC Daemon · single writer"]
        direction LR
        Ledger[("Ledger<br/>append-only JSONL")]
        ActorMgr["Actor<br/>Manager"]
        Auto["Automation<br/>Rules · Nudge · Cron"]
        Ledger ~~~ ActorMgr ~~~ Auto
    end

    subgraph Ports["Control Plane"]
        direction LR
        Web["Web UI<br/>:8848"]
        CLI["CLI"]
        MCP["MCP<br/>(stdio)"]
    end

    subgraph IM["IM Bridges"]
        direction LR
        TG["Telegram"]
        SL["Slack"]
        DC["Discord"]
        FS["Feishu"]
        DT["DingTalk"]
        WC["WeCom"]
        WX["Weixin"]
    end

    subgraph Remote["Remote CCCC Groups"]
        direction LR
        RG1["Trusted group"]
        RG2["Another machine/team"]
    end

    A1 <-->|Native terminal<br/>MCP + protocol| Daemon
    A2 <-->|Native terminal<br/>MCP + protocol| Daemon
    A3 <-->|Browser delivery<br/>Remote MCP| Daemon
    A4 <-->|MCP tools| Daemon
    A5 <-->|MCP tools| Daemon
    Daemon <--> Ports
    Web <--> IM
    Daemon <-->|Group Bridge<br/>messages · read · full| RG1
    Daemon <-->|Group Bridge<br/>messages · read · full| RG2

Key design decisions:

• Daemon is the single writer — all state changes go through one process, eliminating race conditions
• Ledger is append-only — events are never mutated, making history reliable and debuggable
• Ports are thin — Web, CLI, MCP, and IM bridges are stateless frontends; the daemon owns all truth
• Remote groups are explicit trust edges — Group Bridge starts with message-only coordination, and read/full access must be granted per remote group
• Runtime home is CCCC_HOME (default ~/.cccc/) — runtime state stays out of your repo

Supported Runtimes

CCCC orchestrates agents across 17 first-class runtimes, with custom available for everything else. Each actor in a group can use a different runtime.

Runtime	Integration	Entrypoint / Surface
Claude Code	Managed Agent View session + native TUI; per-session MCP	claude
Cline CLI	Auto MCP setup	cline
Codex CLI	Auto MCP setup	codex
GitHub Copilot CLI	Auto MCP setup	copilot
Cursor CLI	Prompt-assisted MCP setup	cursor-agent
Devin CLI	Auto MCP setup	devin
Kiro CLI	Auto MCP setup	kiro-cli
Kilo Code CLI	Prompt-assisted MCP setup	kilo
Antigravity CLI	Prompt-assisted MCP setup	agy
ChatGPT Web	Remote MCP + Browser Delivery	chatgpt.com conversation
Grok Build	Managed ACP session + native TUI; per-session MCP	grok
Hermes Agent	Auto MCP setup	hermes
Droid	Auto MCP setup	droid
Amp	Auto MCP setup	amp
Auggie	Auto MCP setup	auggie
Kimi Code	Auto MCP setup	kimi
OpenCode	Managed ACP session + native TUI; per-session MCP	opencode
Custom	Manual	Any command

These are stable runtime entrypoints or surfaces. CCCC applies runtime-specific launch defaults automatically; actor/profile commands can be reviewed and customized in settings. The Supported Runtimes guide lists the default autonomy flags, including approval-bypass modes such as agy --dangerously-skip-permissions, grok --always-approve, and opencode --auto.

cccc setup --runtime claude       # reports CCCC-owned per-session MCP
cccc setup --runtime cline        # configures Cline CLI MCP for its native TUI
cccc setup --runtime cursor       # shows the prompt-assisted MCP setup contract
cccc setup --runtime kilo         # shows the prompt-assisted MCP setup contract
cccc setup --runtime antigravity  # shows the prompt-assisted MCP setup contract
cccc runtime list --all           # show all available runtimes
cccc doctor                       # verify environment and runtime availability

Choose a Runtime; CCCC derives its interaction surface automatically. CLI Actors expose their native writable terminal. Claude Code, Codex CLI, Grok Build, and OpenCode pair that terminal with a structured background protocol on the same provider session, so users keep direct control while CCCC receives precise lifecycle state. Actor messages enter the native terminal immediately, leaving queue-versus-steer behavior to the receiving Runtime.

For setup commands, interaction details, and troubleshooting for every supported Runtime, see the Supported Runtimes guide.

ChatGPT Web / GPT-5.x as a local development actor

ChatGPT Web can join a CCCC group as a real actor, not just an external chat window: CCCC delivers group messages into one bound ChatGPT conversation via browser delivery, and GPT-5.x calls back through an actor-bound remote MCP connector — receiving routed messages, replying visibly, editing repository files, and running scoped shell/git commands much like a native local coding agent. This also turns spare ChatGPT Web capacity into additional local-development agent capacity.

Setup requires exposing CCCC through a public HTTPS URL for the MCP connector (Cloudflare Tunnel, ngrok, Tailscale Funnel, or a reverse proxy). CCCC defaults to stable text-only delivery and also offers an experimental GPT Pro mode that attaches a tiny blank PNG when delivering each batch. This compatibility workaround does not switch ChatGPT models or guarantee connector availability, and may stop working when ChatGPT changes. Full setup and troubleshooting: ChatGPT Web Model Runtime.

Group Bridge: connect remote groups

Group Bridge extends CCCC from one local working group into a network of trusted groups. A group on your Windows workstation can coordinate with a group in WSL, a Mac, a server, or a teammate's CCCC instance without merging their runtime state or losing the local-first model.

Access is intentionally layered:

Level	What it enables
Messages	Send explicit cross-group messages to the remote foreman, including attachments when needed
Read	Let a trusted remote group inspect local context, repository, and git state through remote MCP tools
Full	Let a highly trusted remote group edit files and run commands through the same local-access surface used by native actors

This makes CCCC useful for multi-machine work, lead/worker coordination across several environments, or trusted team collaboration where one group needs to ask another group for status, evidence, or implementation help. It is not a public guest-access feature: grant read/full access only to remote groups you trust with the target workspace.

Start from Settings > Group Bridge in the Web UI: one side generates a one-time pairing invitation, the other side submits it, and the issuer approves the request. After approval, remote groups appear as explicit recipients, and agents can discover available access with cccc_remote_access(action="list"). For setup steps, message flow, remote MCP tools, and troubleshooting, see the Group Bridge guide.

Messaging & Coordination

CCCC implements IM-grade messaging semantics, not just "paste text into a terminal":

• Recipient routing — @all, @peers, @foreman, or specific actor IDs
• Three explicit modes — Send for active delivery, Send + Reply for a concrete response, and Mail for non-interrupting Inbox delivery
• Separate facts — runtime.delivery, Mail read cursors, replies, cancellations, and task completion never impersonate one another
• Consuming Inbox reads — cccc_inbox_read returns the next ordered Mail batch and advances its Mail cursor atomically
• Reply & quote — structured reply_to with quoted context
• Reply requests — Send + Reply is tracked until the recipient responds or the sender cancels it
• Lifecycle boundaries — paused, stopped, or disabled actors are not silently awakened by delivery
• Remote group recipients — Group Bridge targets appear as explicit remote recipients instead of hidden broadcasts

Use Mail for useful agent updates that can wait, Send when delayed awareness would cost more than interrupting the recipient, and Send + Reply only when a concrete answer is also required. Mail cannot target the human user. One message addresses either user alone or one/more agents—send separate messages instead of mixing those audiences. Use tracked-send when delegated work needs a durable owner, outcome, evidence, handoff, or acceptance trail. @all remains available for announcements or urgent shared coordination, but it should not be the default way to start concrete work.

Push attempts travel through the daemon-managed delivery pipeline. Their runtime.delivery facts remain separate from Inbox read state and replies.

Automation & Policies

A small set of delivery timers and automation rules handles operational concerns without turning every message into a prompt:

Policy	What it does
Mail notice	Sends at most one content-free reminder after a configurable wait for concrete-recipient Mail
Reply notice	Sends at most one reminder for an accepted Send + Reply whose reply is still open
Actor idle detection	Notifies foreman when an agent goes silent
Keepalive	Periodic check-in reminders for the foreman
Silence detection	Alerts when an entire group goes quiet

Beyond built-in policies, you can create custom automation rules:

• Interval triggers — "every N minutes, send a standup reminder"
• Cron schedules — "every weekday at 9am, post a status check"
• One-time triggers — "at 5pm today, pause the group"
• Operational actions — set group state or control actor lifecycles (admin-only, one-time only)

Web UI

The built-in Web UI at http://127.0.0.1:8848 provides:

• Chat view with @mention autocomplete and reply threading
• Per-actor embedded terminals (xterm.js) — see exactly what each agent is doing
• Group & actor management — create, configure, start, stop, restart
• Automation rule editor — configure triggers, schedules, and actions visually
• Context panel — shared vision, sketch, milestones, and tasks
• Group Space — NotebookLM integration for shared knowledge management
• ChatGPT Web Model setup — connect one ChatGPT Web conversation as a CCCC actor
• Group Bridge setup — pair trusted remote groups and choose message/read/full access per connection
• IM bridge configuration — connect to Telegram/Slack/Discord/Feishu/DingTalk/WeCom/Weixin
• Settings — messaging policies, delivery tuning, terminal transcript controls
• Text scale — 90% / 100% / 125% font size with per-browser persistence
• Light / Dark / System themes

Remote access

For accessing the Web UI from outside localhost:

• LAN / private network — bind Web on all local interfaces: CCCC_WEB_HOST=0.0.0.0 cccc
• Cloudflare Tunnel (recommended) — cloudflared tunnel --url http://127.0.0.1:8848
• Tailscale — bind to your tailnet IP: CCCC_WEB_HOST=$TAILSCALE_IP cccc
• Before any non-local exposure, create an Admin Access Token in Settings > Web Access. When no administrator exists, protected APIs are locked; read the one-time code from ~/.cccc/web_bootstrap_token on the host and enter it when creating the first administrator token.
• In Settings > Web Access, 127.0.0.1 means local-only, while 0.0.0.0 means localhost plus your LAN IP on a normal local host. If CCCC is running inside WSL2's default NAT networking, 0.0.0.0 only exposes Web inside WSL; for LAN devices, use WSL mirrored networking or a Windows portproxy/firewall rule.
• Rust launch uses --host / --port overrides first, then the saved Web Access binding (including legacy Python settings.yaml), then CCCC_WEB_HOST / CCCC_WEB_PORT.
• Save stores the target binding. If Web was started by cccc or cccc web, use Apply now in Settings > Web Access to perform the short supervised restart. If Web is managed by Docker, systemd, or another external supervisor, restart that service instead.
• Start / Stop are only for Tailscale remote access and do not rebind the already-running Web socket.
• Token policy is origin-aware: direct loopback browser requests use the local in-memory administrator principal without writing a token, while LAN/public/proxied requests remain fail-closed. Plain HTTP LAN exposure is supported for trusted private networks but still requires an administrator access token; public exposure must terminate HTTPS through a trusted tunnel or reverse proxy.
• Group Bridge pairing is also fail-closed: expired invitations are rejected, credential claim is a ten-minute proof-bound idempotent POST, Rust v2 sessions authenticate a signed challenge/hello/ready transcript and persist downgrade pins on both peers, and public bridge endpoints require HTTPS/WSS.
• External reverse proxies must overwrite client forwarding headers and set CCCC_WEB_TRUST_PROXY_HEADERS=1; supervised CCCC Web processes configure this trust boundary automatically.

Optional membership Reach is a managed public-HTTPS path for Linux and macOS preview users. Local CCCC remains fully usable without an account. First create an Admin Access Token in Settings > Web Access, then open the global Account page, link this installation, and approve its device code on the account site. Return to Web Access to turn Reach on. The equivalent CLI flow remains available:

cccc login
cccc reach on
cccc reach status
cccc reach off

Reach installs a pinned cloudflared helper under CCCC_HOME; it does not upload your ledger or repository. Rust Reach admin links contain a 120-second, one-time, origin-bound exchange code instead of a long-lived Access Token. Windows helper installation is not bundled in this release, so Reach is currently unavailable on Windows.

IM Bridges

Bridge your working group to your team's IM platform:

cccc im set telegram --token-env TELEGRAM_BOT_TOKEN
cccc im start

Platform	Status
Telegram	✅ Supported
Slack	✅ Supported
Discord	✅ Supported
Feishu / Lark	✅ Supported
DingTalk	✅ Supported
WeCom / 企业微信	✅ Supported
Weixin / 微信	✅ Supported

Telegram, Slack, Discord, Feishu, DingTalk, and WeCom support progressive replies; overlong results fall back to lossless final-message chunks. Weixin delivers lossless final messages and currently supports direct bot chats only.

F