Mission control for Claude Code.

CCC runs your fleet of real Claude Code terminals — sessions, autonomous loops, and multi-agent pipelines — from one command deck.

or email us · waitlist@codecc.ai

Sessions

It's a real terminal. We just gave it a command deck.

Real PTY terminals in the browser. Input to stdin, output from stdout, nothing intercepted.

claude — ccc
$ pnpm test
FAIL src/lib/retry.test.ts
✕ retries with exponential backoff (12 ms)
expected 3 attempts, received 1
$ claude "fix the failing retry test"
Reading src/lib/retry.ts…
Editing retry.ts — loop stopped one attempt early
Running pnpm test…
PASS src/lib/retry.test.ts
✓ retries with exponential backoff (9 ms)
Tests: 1 passed, 1 total
$
Browser (xterm.js)Socket.ionode-ptyClaude Code CLI

Specula

Every session, one wall.

Every live terminal tiled on one resizable wall.

web · clauderunning
$ claude "add retry to fetchUser"
Reading src/lib/api.ts…
Editing fetchUser — 3 attempts
api · testsrunning
$ pnpm test
PASS routes/auth.test.ts
PASS routes/user.test.ts
Tests: 42 passed
ralph · iter 7running
story p3-nav — PASS
picking next story…
p3-footer in progress
infra · planwaiting
$ terraform plan
Plan: 3 to add, 0 to destroy
⏸ waiting for approval…
docsidle
deploy complete
$
bigralphrunning
judging working dir…
goal: 8/13 stories hold
refining next loop…
pipeline · nightlyrunning
trigger: cron 02:00
node session — done
node ralph — running
review · pr #214waiting
draft PR #214 opened
+412 −96 · 9 files
⏸ awaiting your sign-off
imagegenrunning
$ ccc images generate
FLUX · hero-poster.png
▓▓▓▓▓░░░░░ 52%
worker-3idle
dial-home ok · gpu idle
$
slack · #ccc-opswaiting
DM from @dana → session
"why did the deploy stall?"
⏸ waiting for input…
auditidle
token ledger synced
$

Intents

Write the intent. Review the PR.

Describe the outcome. CCC researches the repo, writes the plan, executes it, and opens a PR for your sign-off.

01 · intent

new intent

Rate-limit the public API, behind a config flag, with tests.

02 · research

researching repo
  • src/api/router.tsread
  • src/api/middleware/auth.tsread
  • src/config/flags.tsread
  • src/lib/redis.tsread
  • test/api/router.test.tsread

03 · plan

plan.md
  1. 1. Add limiter middleware (token bucket)
  2. 2. Wire RATE_LIMIT flag into config/flags.ts
  3. 3. Mount on public routes only
  4. 4. Cover burst + steady-state in tests

04 · execute

prd.json
  • limiter middleware addedpasses: true
  • config flag wiredpasses: true
  • public routes coveredpasses: true
  • tests passpasses: true

05 · review

feat: rate-limit public API behind config flag

ccc/intent/rate-limit → main

+412−879 files changedawaiting your sign-off

Autonomy

Loops that don't fool themselves.

RalphBigRalphrefined goalgoal met ✓judgement memoryjudgement

Ralph

Fresh-context iteration against a PRD until every story passes.

BigRalph

A skeptical second session inspects the real working dir after each run, judges the original goal, and refines the next loop. It remembers.

Autopilot

Put the repo on autopilot. Keep the stick.

One reviewable draft PR at a time. Never merges on its own.

improver

Captain

Scans the repo, picks the next improvement, and opens the draft PR.

reviewer

First Officer

Reviews the Captain's diff and posts findings before it reaches you.

QA

Flight Engineer

Verify-only: runs the checks and reports back. Never opens PRs.

  1. #41merged by you
  2. #42merged by you
  3. #43merged by you
  4. #44draft

Pipelines

Wire agents together. Visually.

A visual DAG of Ralphs, sessions, gates, and imagegen nodes passing {{variables}} on a shared blackboard.

triggercron | webhook | intervalsessionClaude Code PTYRalphfresh-context loopgatehuman approvalBigRalphjudge & refineimagegenstable-diffusion.cpp

Forge

Skills earn their place.

Challenger skills fight the champion on golden tasks. You promote. Rollback is instant.

Golden-task scoreboard: challenger@v4 passes 5 of 6 golden tasks against champion@v3's 4 of 6. Promotion stays human gated — you decide.

Knowledge

The memory layer.

Intelligence

Mines your session history into a ranked what-to-work-on-next, plus a yesterday recap.

LLM Wiki

A living knowledge base auto-linked to projects and sessions.

Research

Long-running deep-research agents that return cited reports.

Ask the Codebase

Local-embedding RAG with file:line citations verified at answer time.

src/pty/manager.ts:214 ✓ verified

Platform

Runs on your hardware.

Worker Nodes

Pool your GPUs. Dial-home nodes serve local models; CCC routes each job to the best fit.

Media

FLUX & ERNIE images and Wan2.2 video, generated locally via stable-diffusion.cpp.

Local inference

Flip the router from cloud to local models. Offline mode built in.

cloud → localoffline mode

Computer Use

Isolated desktop control on Linux, Windows, macOS, or Docker — never your operator console.

Surfaces

The deck follows you.

DM a bot, get a session. Per-project channels. Policies decide who can touch what.

  • Slack
  • Discord
  • MCP
  • 55 tools
  • CLI
  • tray
  • Local Agent PWA
  • Remote Hosts

G2 glasses

voice: "approve"

Fleet HUD on your face. Dictate prompts, approve permission requests, hands-free.

Governance

Autonomy you can audit.

License

Pick your license.

Free

Personal & noncommercial

Everything in CCC, free for personal use under the PolyForm Noncommercial license.

Commercial

Licensed

Running CCC at work? Join the waitlist and we'll reach out about commercial licensing.

$ join --waitlist

Take command.

or email us · waitlist@codecc.ai