# 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

Repository: https://github.com/ChesterRa/cccc
Canonical: https://ross.abutalabs.com/products/cccc
Homepage: https://cccc.sh/
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: ai-agents, claude-code, codex-cli, gemini-cli, group-chat, llm-orchestration, local-first, multi-agent, opencode, zero-infra, chatgpt
Last push: 2026-09-02T08:35:48+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 27
- inputs: {"age_days": 383, "days_push": 0, "days_rel": 1, "gap_med": 3.0, "n_releases_24m": 73}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1094, forks 92 (observed 2026-09-03T02:15:05.256764+00:00)

## What it is
CCCC is a Python-based multi-agent orchestrator that coordinates coding agents (Claude Code, Codex CLI, ChatGPT Web, Gemini CLI, and 13+ other runtimes) like a group chat, with durable append-only ledgers, read receipts, and delivery tracking. It provides a unified control plane via Web UI, CLI, MCP, and IM bridges, installable with a single pip command and requiring no infrastructure.

## Use cases
- coordinate multiple coding agents as a team
- run claude code and codex together on shared tasks
- monitor long-running agent workflows from my phone
- track which agent read and replied to which message
- orchestrate ai agents across machines without infrastructure
- assign tasks to a foreman agent and parallelize work
- bridge chatgpt web sessions into local agent workflows
- keep agent context out of terminal scrollback

## When to choose
- you run multiple coding agents and lose context across terminal sessions
- you need durable, auditable coordination with delivery and read semantics
- you want one pip install with zero infrastructure and local-first state
- you need remote/mobile supervision of 24/7 agent workflows
- you want cross-vendor agents (Claude, Codex, ChatGPT Web, custom) in one group

## When to avoid
- you only run a single coding agent with simple prompts
- you need a heavyweight distributed multi-agent platform with centralized cloud orchestration
- you require formal multi-agent frameworks with planner/executor abstractions rather than chat-style coordination
- your environment cannot run a local daemon

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, mcp, chat-interface, workflow-automation, developer-tools, cli, web-framework
- domain: developer-tools, large-language-models, self-hosted
- platform: python, cli, self-hosted, cross-platform, windows
- tags: multi-agent-orchestration, claude-code, codex-cli, gemini-cli, group-chat, local-first, append-only-ledger, zero-infrastructure, mobile-ops, im-bridges, foreman-pattern, ai-agents, automation, web-server, macos, linux

## Member repositories
- ChesterRa/cccc (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:05.256764+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:49:30.301017+00:00, confidence not recorded.
  - readme: https://github.com/ChesterRa/cccc (fetched 2026-09-03T02:15:05.256764+00:00, sha e0bfa7aa67af)
  - homepage: https://cccc.sh/ (fetched 2026-08-29T12:52:24.825862+00:00, sha ee02e7951331)
- Data as of 2026-08-30T08:39:29.467469+00:00.