Now on macOS, Windows, Linux and web

Run a fleet,
command the operation.

Control Center is the native deck for your whole developer operation. Dispatch coding agents onto isolated worktrees, review what they ship and keep tickets, meetings and pipelines in one quiet, well-instrumented place.

Free and open source · macOS, Windows, Linux and web

Shot 01The deck
Screenshot to capture

Full app window, light theme, real data: sidebar with the pillar rail, the agents grid with live status pills (running, blocked, done), one agent transcript streaming on the right, today's meetings in the agenda and the token-cost ticker in the header.

→ public/shots/01-dashboard.pngPlaceholder
100+
MCP tools, spoken by any client
0
Cloud dependencies; ML runs on-device
3
Clients: desktop, web and phone
1
Server, the single source of truth
Every stream of work

One deck for the whole operation.

Agents are one pillar among co-equal ones. The same vocabulary (status, ownership, next action) carries across all of them.

Agents

See what every agent is doing.

Each agent runs on its own branch, in its own copy-on-write worktree. Thinking, running, blocked, failed, idle: every state reads differently at a glance, with live token cost and last-output age per run.

  • Presence is earned by representing the agent model truthfully, never by decoration.
  • Steer a run mid-flight, take over, or hand it back.
  • Ownership and attribution stay legible as teammates join.
Shot 02Agents
Screenshot to capture

The agents grid mid-flight: six agent cards with status pills (two running, one blocked on an approval, the rest done), a live transcript streaming in the side panel and per-run token cost in the card footer.

→ public/shots/02-agents.pngPlaceholder
Review

Review and merge what the fleet ships.

Priority pull requests surface first. Read the diff, drop inline comments, dispatch reviewer agents and land a ship / hold / block verdict without leaving the deck.

  • Inline threads with GitHub sync and suggested edits.
  • AI reviewers with P0–P3 findings and a rolled-up verdict.
  • An ephemeral focus mode for distraction-free review.
Shot 03PR review
Screenshot to capture

The review surface on a real diff: syntax-highlighted hunks, two inline comment threads, an AI reviewer’s rolled-up verdict with P0–P3 findings and the ship / hold / block actions in the header.

→ public/shots/03-review.pngPlaceholder
Meetings & calendar

Your day and your meetings, on the same deck.

Record a call and the deck transcribes it on-device, separates the speakers and writes the summary, decisions and action items. Connect Google Calendar to see your day and turn any event into a recorded, summarized meeting.

  • On-device transcription and diarization; audio never leaves your machine.
  • Google Calendar in month, week and agenda views, with RSVP.
  • A heads-up before each meeting and record-and-link straight from an event.
Shot 04Meetings & calendar
Screenshot to capture

A recorded meeting’s notes next to the calendar week: diarized transcript with speaker names, the AI summary, extracted action items with owners and the on-device privacy marker.

→ public/shots/04-meetings.pngPlaceholder
Pipelines

Orchestrate the fleet as a DAG.

Compose steps into a graph: prompt an agent, run a script, fan out reviewers, join the results. Runs start by hand, on a schedule, or off a domain event and every node carries its own retry and continue-on-fail policy.

  • Three triggers: manual, scheduled, or domain-event.
  • Router and join nodes for conditional, parallel work.
  • Resumable runs that survive a restart mid-flight.
Shot 05Pipelines
Screenshot to capture

Plan Studio with a pipeline run in flight: the DAG with trigger, fan-out reviewers and join nodes, one node mid-retry showing its attempt counter and the per-run cost rollup at the bottom.

→ public/shots/05-pipelines.pngPlaceholder
And the rest of the day

The small pillars, held to the same bar.

05

Tickets

One vendor-agnostic ticket carries work from request to merge: two-way Linear sync, a coupled pipeline run and an execution lock so two agents never claim the same work.

Read the guide
06

Channels & multiplayer

Humans and agents share one roster as co-equal principals. DM an agent, spin up a channel per worktree, follow a teammate’s cursor and steer a run mid-flight.

Read the guide
07

Inbox & newsfeed

A unified inbox across every pillar, a ⌘K omnibox to act from anywhere and RSS feeds folded into the same triage flow. Nothing waits in a tab you forgot.

Read the guide
The platform

Four systems that keep a fleet legible.

Agents, review and pipelines all sit on the same foundation. Each system exists so a run starts with more context and you keep more control, than the run before it.

01Memory

Memory that compounds across runs.

Every workspace keeps facts, policies and domains in one hybrid store: full-text and vector search over a knowledge graph. An agent opens its run with the context the last run earned, gated to exactly what its role may read.

FTS5Vector · 384-dimRole-gated
02Code graph

Your codebase, read as a graph.

A tree-sitter symbol-and-edge index per repo lets an agent jump from a symbol to its callers, callees and blast radius before it edits a line: the same impact view you get when you review the result.

Tree-sitterCallers + calleesImpact radius
03Open tool surface

One hundred tools, one open protocol.

A JSON-RPC server exposes agents, review, the code graph, memory and ticketing to any MCP client. Mode gating and approval prompts sit in front of every call, so a tool never outruns the policy you set.

100+ toolsJSON-RPCMode-gated
04Sandbox

Secure by construction.

Each channel runs inside an OS-native sandbox (Seatbelt on macOS, bubblewrap on Linux) over copy-on-write worktrees. Credentials are minted per launch, capability-gated, brokered in memory and revoked on teardown.

Seatbelt / bubblewrapCoW worktreesEphemeral credentials
Get started

Every screen you own, one operation.

The same app runs native on macOS, Windows and Linux, in the browser at app.usectrl.dev and as a phone companion. Every client is a thin renderer over one cc_server that owns your data.

macOS

Control-Center-<v>-arm64.dmg

Apple Silicon · macOS 13+ · signed and notarized

Download .dmg

Windows

Control-Center-<v>-x64-setup.exeControl-Center-<v>-windows-x64.zip

x64 · Windows 10+ · portable zip also available

Download .exe

Linux

Control-Center-<v>-x86_64.AppImageControl-Center-<v>-linux-x64.tar.gz

x86_64 · tar.gz also available

Download AppImage

Self-hosting? Every release also ships the headless cc_server for macOS, Linux and Windows, plus Docker images on GHCR. See Run a headless server.

Free and open source · auto-updates on desktop

New to Control Center? Start with the quick-start guide, or browse the full documentation.

Speaks the tools you already run
GitHubLinearMCP · 100+ toolsClaude CodePi
Start today

Take command of the fleet today.

Free and open sou andDesktop on macOS, Windows, and Linux; the same app in your browser and on your phone.

GitHub

Source, issues and releases. Star the repo to follow along.

Star on GitHub

Documentation

The full manual: guides, concepts and the MCP tool reference.

Open the manual

Changelog

What shipped, release by release, with the reasoning attached.

Read the changelog