EARLY ACCESS · WINDOWS

Command a fleet
of coding agents.

DAI is a desktop cockpit that runs Claude Code, Codex and Grok side by side. Coordinated swarms, an agent-driven browser, remote servers over SSH, and one agent that runs it all and proves its results against your tests.

Read the docs
✓ BYO subscriptions, no API keys ✓ Local-first: your code stays home ✓ Claude · Codex · Grok · shell

One membership · Code · Voice · Assistant · Creator · Workspace · Business · Hub

⌁ Meet the DAI Agent

One input.
Verified results.

The DAI Agent is an operator for the whole cockpit, not a chat box bolted to the side. It answers from your repo, takes on real work, and proves the result with your own tests.

  • Ask anything and get an answer straight out of your repo.
  • Hand it real work. It dispatches coding tasks and streams every step live, and cancel is always one click away.
  • It runs your project's own test suite against every result before you see it.
  • Nothing touches your working tree until you hit Apply.
  • It drives the whole cockpit: panes, panels, spaces, even the browser.
  • And it learns: every task it completes makes the next one better.
Get it with Pro
⌁ DAI AGENT
PRO EXCLUSIVE
ship the auth fix
checkout-service queued
add rate limiting
api-gateway queued
cover checkout with tests
checkout-service queued
fix the flaky queue test
worker queued
wire the OAuth callback
dashboard queued
tighten the CSP headers
web queued
ship the auth fix
checkout-service queued
add rate limiting
api-gateway queued
cover checkout with tests
checkout-service queued
fix the flaky queue test
worker queued
wire the OAuth callback
dashboard queued
tighten the CSP headers
web queued
ship the auth fix
checkout-service ✓ VERIFIED · tests green
add rate limiting
api-gateway ✓ VERIFIED · tests green
cover checkout with tests
checkout-service ✓ VERIFIED · tests green
fix the flaky queue test
worker ✓ VERIFIED · tests green
wire the OAuth callback
dashboard ✓ VERIFIED · tests green
tighten the CSP headers
web ✓ VERIFIED · tests green
ship the auth fix
checkout-service ✓ VERIFIED · tests green
add rate limiting
api-gateway ✓ VERIFIED · tests green
cover checkout with tests
checkout-service ✓ VERIFIED · tests green
fix the flaky queue test
worker ✓ VERIFIED · tests green
wire the OAuth callback
dashboard ✓ VERIFIED · tests green
tighten the CSP headers
web ✓ VERIFIED · tests green
LIVE ACTIVITY
task received — routing to the right lane

every task passes the scan: dispatched → tested → verified → yours to apply

5 AGENTS
one goal, spawned in one click
5 BRANCHES
each agent isolated on its own
14/14
tests green on the merged result
PASS
reviewer-approved, coordinator-merged

receipts from one real swarm run, screen-recorded. you can watch the footage instead of taking our word for it.

The cockpit

Everything an
agent team needs.

DAI treats agents like a team you direct. Many hands, one board, one screen.

Parallel panes

Run several agents on several problems at once, in real terminal sessions in a drag-and-drop grid rather than tabs you have to babysit. Here: Claude shipping a fix while Codex reviews and vitest re-runs on every edit.

DAI cockpit with Claude, Codex and shell panes working in parallel
real session

Swarms

One click spawns a role-primed team (coordinator, builders, reviewer) on a shared board, each agent on its own git branch.

Agent-driven browser

An embedded browser your agents can see, click and screenshot. Point at any element and the exact selector lands in your prompt.

Remote over SSH

Point a space at any server. Panes spawn there, the file tree follows, and your workflow doesn't change.

MCP, managed

Discover servers with a real handshake, toggle them per space, authorize OAuth in-app. Secrets live in your OS keyring.

Panes are permanent

A local database backs every session, so you can switch spaces all day without anything restarting. Scrollback survives. Local-first, with no cloud backend.

The swarm board, live

DAI swarm board with five agents, branches and completed tasks
real session

A space running on a server

DAI workspace running Claude Code and a shell on a remote server over SSH
real session
No mockups

Shot inside the real app.

screen-recorded product footage. a fresh film ships with the next release

Simple pricing. Serious leverage.

One membership for every DAI app. You bring your own agent subscriptions. DAI never proxies model traffic.

Trial
Every feature, 7 days
$0 for 7 days
  • Every Pro feature, in every DAI app
  • No card, no commitment
  • One trial per account
  • Your work stays intact when the trial ends
Join the waitlist
One membership
Pro
The whole suite
$39 /month
  • One membership for Code, Voice, Assistant, Creator, Workspace, Business and Hub
  • ⌁ The DAI Agent
  • Bring your own agent subscriptions — DAI never proxies model traffic
  • Bench and OS when they ship — not sold separately
Join the waitlist
Team
Your whole crew
$49 /seat/month
  • Same apps as Pro, on every seat
  • Minimum 2 seats
  • Orgs, roles and shared workspaces
  • Central billing and admin
Join the waitlist

Prices in USD, excluding VAT. One membership for the entire suite. Every plan is bring-your-own-subscription for the agent CLIs, and DAI never proxies your model traffic. When a trial ends or a plan is cancelled you drop to a free tier that keeps all your work readable. Hub Stripe checkout is parked — the waitlist is the signup path for now.

Questions, answered.

What is the DAI Agent?

An operator built into DAI on the Pro plan. One input: it answers from your repo, dispatches real coding tasks with a live activity feed, runs your project's own test suite against every result, and only touches your working tree when you hit Apply. It also drives the app itself (panes, panels, spaces, the browser) and gets better with every task it completes.

Do I need API keys?

No. DAI drives the official CLIs (Claude Code, Codex and Grok) with the subscriptions you already pay for. DAI never proxies your model traffic and never marks up tokens.

Where does my code and data live?

On your machine. Workspaces, panes and swarm state are stored in a local database under your user profile; secrets go in the OS keyring. DAI has no cloud backend reading your code.

Which agents are supported?

Claude Code, Codex and Grok CLIs out of the box, plus plain shell panes for anything else. DAI detects the CLIs installed on your machine.

What platforms does DAI run on?

Windows 10/11 today. macOS and Linux are on the roadmap. Remote workspaces already let your panes run on any POSIX server over SSH.

How is DAI different from an AI chat IDE?

Chat IDEs give you one assistant in one window. DAI orchestrates many real agent sessions in parallel, with swarm coordination, an agent-controllable browser, remote machines, and the DAI Agent operating the cockpit itself. One membership also covers Voice, Assistant, Creator, Workspace, Business and Hub — Bench and OS come later.

Join the waitlist