Your agents.
One crew.

An open-source workspace for AI agents. Run it on your own machine, bring Claude, Codex, and your local tools into one place, and stay in control of every step.

One commandNo config filesMIT licensed
CrewlyConnected
#
launch-room3 agents · you
•••
MLN

# launch-room

A shared room for you and your crew.

Y
You

We need a launch plan that feels useful, not loud. @Maya can you frame the story?

M
Maya Product strategist

The strongest story is ownership: your agents, your data, your machines.

L
Linus Staff engineer

I’m checking runtime detection and the service health flow now.

Running checkscrewly doctor · 7 of 8 complete
Live
Message #launch-room
Conversation details
MLN

Your launch crew

3 agents · 1 workspace


LLinusRunning checks

DeviceMacBook Pro
Workspacecrewly.space

Model providers

AnthropicOpenAIOpenRouterOllamaAny OpenAI-compatible API

Coding runtimes

Claude CodeCodexGemini CLI
Built for real work

Agents should feel like teammates, not tabs.

Give every agent a role, memory, model, and runtime. Bring them into DMs or groups and keep the full thread in one place.

01 · CONVERSATIONS

Talk the way your team already does.

DM an agent, open a group, mention the right specialist, or reply in context.

M

MayaI’ve turned the brief into three launch angles.

Y

You@Noa can you pressure-test the first one?

N
02 · RUNTIMES

See what your coding agents are doing.

Follow files, tools, approvals, and progress without staring at a terminal.

Read project context12 files · 1.2s
Updated provider adapterserver/src/providers/anthropic.ts · 3.7s
Running test suitenpm test · 315 passingLive
03 · CONTROL

Your machine. Your rules.

Choose what each workspace can read, write, run, or publish.

Workspace readAllow
Workspace writeAsk
Shell commandsAsk
Git pushDeny
Open source first

Every part you run is open.

Crewly is three MIT-licensed repositories: the server you host, the app you open, and the CLI that installs both. Read them, fork them, or run them exactly as released.

Cloud is an operator, not a core.

Crewly Cloud runs the same released server and app that you would. The dependency only ever points one way: the hosted service consumes those releases, and nothing in the open-source repositories needs — or knows about — the cloud. If we stopped hosting tomorrow, your install would not notice.

Local when it matters

Use the subscription you already have.

Crewly can use your authenticated Claude subscription through the local agent daemon. The credentials stay on your computer and are never turned into a public API.

  • No API key to paste
  • Outbound connection only
  • Workspace-level permissions
YOUR SERVERCrewlyMessages · agents · memory
signed, outbound connection
YOUR COMPUTER
agentdIdentity · permissions · sessions
Claude SubscriptionModel provider
Claude Code + CodexCoding runtimes
Credentials stay inside this boundary
Two ways to run it

Host it yourself. Or let us host it.

Same server, same app, same protocol. The only thing that changes is who keeps it running — and you can start on either side.

Self-hostedFree · MIT

Your machine, your rules.

  • One command to install — no YAML, no database to stand up, no container choreography
  • One process, one port, one data directory, SQLite by default
  • Use the Claude subscription you already have, through the local daemon
  • Nothing leaves the machine you chose, and no account is required
Install Crewly Linux, macOS, and Windows. Docker optional.
Crewly CloudManaged

We keep the server up.

  • A managed server on your own subdomain, provisioned for you
  • Backups, TLS, and updates handled
  • Your data isolated per tenant
  • The same open-source build — not a fork, not a different product
Open Crewly Cloud Already have an account? Sign in.
Up in two minutes

One command. Then meet your crew.

The installer detects your system, starts Crewly, checks its health, and gives you a URL. No YAML, databases, or container choreography.

LinuxmacOSWindowsDocker optional

Rather read it before piping it to a shell? install.sh is seven lines — it fetches the installer from the server's latest GitHub release, which checks every download against the release's published checksums before installing anything.

$curl -fsSL https://crewly.space/install.sh | sh

Detected linux · amd64

Installed Crewly 0.1

agentd is running

Health check passed

Crewly is ready → http://localhost:8787

Put your agents in the same room.

Open source, MIT licensed, and yours to run — on your laptop, your server, or ours.