For non-developers who run AI coding agents

VibeCodeDeckVibe coding, from one deck.

One person, a dozen agents, one window. VibeCodeDeck sits on top of the coding agents you already run, from Claude Code to Codex, so you direct a whole fleet instead of babysitting one terminal. Not another editor. Not another model.

Windows macOS
VibeCodeDeck 1 problem api needs you docs finished─▢✕
‹ 4 Tall FitAllRunStopRestartServersClearPortsCacheSettingsCLIsBoardMore
Batches: 3 of 6 doneDone 1–3Working 4, 5Waiting 6Results 3All batches ▾
Decks1Deck+Projects+AnnaAnnaCloudSwarmAuditLibraryPluginsConnect
web-app+On
1✕✕+
● Update(components/Header.tsx)
⎿ Updated with 18 additions and 4 removals
● Update(app/layout.tsx)
⎿ Updated with 6 additions
● Bash(npm run build)
⎿ ✓ compiled successfully in 4.2s
… +12 lines (ctrl+o to expand)
✻ Crunching… (2m 14s · ↓ 3.1k tokens)
> make the header stick to the top
⏵⏵ auto mode on (shift+tab to cycle)
api+On
✕+
› add a plan tiers table
• Ran npx supabase migration new plan_tiers
└ Created migrations/0007_plan_tiers.sql
Would you like to run the following command?
$ npx supabase db push
› 1. Yes, proceed
2. Yes, and don't ask again for this command
3. No, and tell Codex what to do differently
Press enter to confirm or esc to cancel
payments+86%On
2✕✕+
● Read(app/checkout/route.ts)
⎿ Read 214 lines
● Bash(npm test -- checkout)
⎿ ✓ 24 passed, 0 failed (6.1s)
… +31 lines (ctrl+o to expand)
✢ Deliberating… (3m 08s · esc to interrupt)
⎿ Tip: use /btw to ask a side question
> now handle the refund case too
⏵⏵ accept edits on (shift+tab to cycle)
docs+On
1✕+
● Done:
- pricing/page.tsx - added the yearly plan
- faq.tsx - answered the refund question
Next:
- read it over and tell me what to cut
✓ Committed 2 files
✻ Worked for 4m 12s · done 9:04 PM
> ▊
⏵⏵ auto mode on (shift+tab to cycle)
BoostsResearchAuditTaskReposGapsCompareValidate Edit
Ask Anna about your projects or send context to a chat Talk to Anna
Claude Daily 42%
Claude Weekly 61%
Codex Daily 18%
Codex Weekly 33%
Claude Code
Codex
Grok
Gemini
Kimi
Antigravity
The bottleneck

One agent at a time is the slow way to build.

You kick off a task, then wait. The agent stalls on a yes/no question and you find out ten minutes later.

One agent, one terminalmostly waiting
Twelve agents on VibeCodeDeckmostly working
What it is

One window for every agent you run.

VibeCodeDeck is a desktop cockpit for AI coding agents. Instead of juggling a dozen terminal windows, you launch, watch and steer all of them from a single grid - and it tells you the moment one needs a human.

Launches

Claude Code, Codex, Grok, Gemini and more, plus your app running live.

/12 panes, 1 window

Watches

Reads each agent's output and flags working, idle, waiting or done.

/working · waiting · idle

Controls

Run, stop or restart the whole fleet, or hand a deployed plan out one batch per agent.

/Run · Stop · Restart · Clear

Remembers

Prompts, layouts and sessions come back exactly as you left them.

/restored on launch

Built for non-developers

You do not need to know how any of this works.

VibeCodeDeck was built for the people actually shipping software with AI right now, most of whom have never written a line of it. Everything below exists because that is who is using it.

Everything in plain English

No jargon anywhere in the app. Every button says what it does, and every warning tells you what actually goes wrong if you ignore it.

You cannot break what works

Give an agent its own copy of your project. Nothing it does touches the live version until you look at it and say yes.

An undo button for your whole project

Take a save point before anything risky. If the AI makes a mess, you jump back to exactly how it was.

It tells you what is unsafe

The audit asks fifteen questions a developer would ask, in words you already understand, and hands the answers back for the AI to fix.

Where it fits

Not another editor. Not another model.

VibeCodeDeck sits on top of the AI coding tools you already use, so you direct a whole team of them instead of watching one.

AI editors

Cursor, Windsurf

You do the typing and the AI helps as you go. One person, one file at a time.

Coding agents

Claude Code, Codex

They write the code for you. Powerful, but it is one agent in one black window, and you have to sit and watch it.

The control deck

VibeCodeDeck

Runs a dozen of those agents at once. See what every one is doing, hand them a whole plan to work through, and get told the moment one is stuck or has broken something.

Features

A whole control room, not a launcher.

Everything you need to run a fleet of agents at once - without the chaos.

Run the whole fleet

  • Up to 12 agents in one grid
  • Claude, Codex, Grok, Gemini and 4 more
  • Your app's live preview runs here too
  • Several agents inside one box
  • Up to 6 decks, one click apart

Never miss a beat

  • Three alert levels, three sounds
  • Jump straight to the waiting agent
  • One alert when the fleet finishes
  • A live status light on every pane
  • Context meter, clear before it fills

Steer them all

  • Ask Anna to brief any chat for you
  • Full access per tab, when you trust it
  • Hand a stuck job to a different AI
  • Search every terminal at once
  • Restart or clear a pane

Swarms and boosts

  • One task, a lead agent plus a team
  • Every one on its own copy, no clashes
  • Boosts: extra instructions for a harder pass
  • Bring all the work together in one click
  • Publish the result straight to GitHub

Check it before you ship

  • 15 reviews, one agent per risk
  • Safety check: the 9 that block launch
  • One report, ranked worst first
  • Reopen any saved report later
  • Hand the findings back to Claude

Change things safely

  • Each agent gets its own copy to work on
  • Wrap up a long chat and start it fresh
  • Tweak anything yourself before it lands
  • Save points to jump back in time
  • Plugins that plan and debug first

Hand it a whole plan

  • Drop in a plan, one agent per batch
  • Batches wait for the ones they need
  • Choose how many run at once
  • Each batch shows its own progress
  • Every summary in one Results view

Every project set up right

  • Each project gets its own preview address
  • Your users' crashes, sent to the agent
  • Edit the notes your AI reads first
  • Your app running, right inside the box
  • Click anything, say what to change
  • A to-do board and notes per project

More power, less mess

  • Keep an agent going with the laptop shut
  • Talk to Anna instead of typing
  • One library for prompts, notes and files
  • Several logins per AI, usage for each
  • Clears the junk that fills your disk
  • Everything comes back when you reopen
Before you launch

Find what will bite you, before your customers do.

Open the Audit deck and up to fifteen agents review your project, one risk each, skipping any check that does not apply to it. They come back as a single report, ranked worst first, in plain English. Then you hand the findings straight back to an agent to fix.

Safety check - the 9 that block a launchFull audit - all 15 reviews
blocks launch

Can another customer see your customers' data?

Goes through every place your app fetches data and asks whether it filters to the person logged in. Miss one and customer A sees customer B.

blocks launch

Is your database actually locked?

Reads your database rules table by table. A rule switched on but left empty looks locked and silently returns nothing to everyone.

blocks launch

Are your secrets in your users' browsers?

Hunts for API keys and passwords that have escaped into the code every visitor downloads.

blocks launch

Can someone get your product without paying?

Looks for ways to reach the paid features for free, and ways to keep them after cancelling.

blocks launch

How many unlocked doors does your app have?

Counts every way into your app and reports how many actually check who you are. A real count, not a guess.

blocks launch

Can a stranger's input break your app?

Finds the places where whatever a visitor typed gets treated as trustworthy and passed straight through.

blocks launch

Can a stranger run up your bill overnight?

Finds anything a stranger can hit over and over that costs you money: AI calls, emails, uploads, lookups.

blocks launch

What did your app download, and is any of it poisoned?

Checks the outside code your project pulled in for packages it should not be trusting.

blocks launch

If your AI feature is tricked, what can it reach?

Works out what someone could get your AI feature to do for them, just by talking to it.

full audit

Is your app already quietly wrong?

Looks for answers that are wrong today and nobody noticed, plus the spots that fall over once fifty people show up at once.

full audit

Does your app admit when it breaks?

Finds failures nobody is told about, not you and not the customer. The payment that never arrived, the email that never sent.

full audit

Does your app do what you promised about people's data?

Holds your privacy page up against your actual code and reports where the two disagree.

full audit

Are you selling to consumers legally?

Checks the concrete mechanics of selling to the public: cancelling, refunds, renewals and what you have to show before someone pays.

full audit

Is your business allowed to exist on the rails you built it on?

Checks whether the payment processors and platforms you depend on actually permit the kind of business you are running.

full audit

Can everyone actually use it?

Finds where people with disabilities are shut out, kept in proportion rather than dumped on you as a wall of warnings.

Swarms

One task, a whole team of agents.

Give one instruction and VibeCodeDeck launches a lead agent plus a set of workers, each on its own safe copy of the project so they cannot tread on each other. When they are done, merge all of it back in one action and push it to GitHub.

01

A lead plus workers

Two to five agents: one coordinator and a small team. You pick who runs as Claude, Codex, Grok or another tool.

02

Each on its own copy

Nobody overwrites anyone else. When they are done, you merge the good work back.

03

A decision

Answers a should-we question. Picks one option and says why, in plain English.

04

An action plan

Ordered steps you can start on, with the files and the risk named.

05

A research brief

What is true, with sources, and a clear list of what is still unknown.

06

Merge when they are done

One action brings the team's work back into your project. You look first.

From the left side of the app

Launch a swarm from the left rail. Boosts are separate: extra instructions you add to one agent so it works a task harder.

Run 12 agents across8 tools in1 window, and check0 tabs to know who needs you.

How it helps

Less waiting. More shipping.

The difference between running one agent and commanding a fleet.

Without VibeCodeDeck

One agent at a time

The other eleven projects sit still while you wait.

With VibeCodeDeck

Up to 12 agents in parallel

Twelve projects moving together in one grid.

Without VibeCodeDeck

Tab-hopping to check progress

A window each, checked in rotation, all day.

With VibeCodeDeck

Every status at a single glance

A live light on each pane: working, idle, waiting, done.

Without VibeCodeDeck

Agents stall unnoticed for minutes

It asked you a yes/no question ten minutes ago.

With VibeCodeDeck

Instant ping the moment one needs you

Red, amber or blue in the title bar, each with its own sound.

Without VibeCodeDeck

Lose context and layout on restart

A blank chat that knows nothing about yesterday.

With VibeCodeDeck

Sessions and layout resume automatically

Reopens the actual conversation, not a blank chat.

Without VibeCodeDeck

Guessing how close you are to a limit

You find out you ran out halfway through a task.

With VibeCodeDeck

A live plan-usage meter, always visible

Daily and weekly windows, for every account you use.

How it works

Up and running in three steps.

01

Pick a project for each box

Click a box in the grid and choose the folder your project lives in. That is the whole setup.

02

Start your agents

Choose which AI runs in each box and hit go. Up to twelve at the same time.

03

Get on with your day

They keep working. VibeCodeDeck taps you on the shoulder only when one of them needs an answer.

Who it's for

Built for people who live in the terminal.

Founders building their own thing

You had the idea. Now twelve agents build it while you decide what matters next.

Vibe coders

No computer science degree, no team. You describe it, the AI writes it, VibeCodeDeck keeps it from going wrong.

Freelancers and agencies

One deck per client. Several projects moving at once without a window for each.

Designers and product people

Ship the change yourself instead of waiting your turn in someone else's queue.

Pricing

Simple pricing. Cancel any time.

Every feature on every plan. No add-ons, no seats to count.

Monthly
$29/month

Billed every month. Cancel whenever you like.

Get started
YearlySave 28%
$249/year

Works out at about $20.75 a month, billed once a year.

Get started
Founder lifetimeOnly 100 available
$499once

Pay once and keep it for good, updates included. For the first 100 buyers only.

Get started

Included on every plan

  • Up to 12 agents at once
  • Alerts the moment one needs you
  • Swarms, boosts and batch plans
  • The 15-check audit before you launch
  • Safe copies and save points
  • One library for prompts, notes and files
  • Spend meters, so no surprise bills
  • All future updates
FAQ

Questions, answered.

Do I need to know how to code?

No. VibeCodeDeck is built for people who describe what they want and let the AI write it. Every button, warning and report is in plain English, and the risky things are behind a safety net: agents work on their own copy, and you can take a save point and jump back if it goes wrong.

What exactly is VibeCodeDeck?

A desktop app for Windows and macOS that runs a grid of AI coding agents at the same time, with alerts, a spend meter, one library, swarms, a pre-launch audit, safe copies and automatic resume built in.

Which agents does it work with?

Claude Code, Codex, Grok, Gemini, GitHub Copilot, Qwen, Kimi and Antigravity. It drives the ones already installed on your computer - VibeCodeDeck is the cockpit around them, not another AI you pay for.

Which platforms does it run on?

Windows 10 or 11, and Macs with Apple silicon (M1 or newer). Linux may follow.

How does billing work?

$29 a month, or $249 a year which saves you 28%. The first 100 buyers can also pay $499 once for Founder lifetime access. Every feature is included on every plan - there are no add-ons and no seats to count. Monthly and yearly can be cancelled any time.

The deck

Twelve agents. One window.

VibeCodeDeck 1 problem api needs you docs finished─▢✕
‹ 4 Tall FitAllRunStopRestartServersClearPortsCacheSettingsCLIsBoardMore
Batches: 3 of 6 doneDone 1–3Working 4, 5Waiting 6Results 3All batches ▾
Decks1Deck+Projects+AnnaAnnaCloudSwarmAuditLibraryPluginsConnect
web-app+On
1✕✕+
● Update(components/Header.tsx)
⎿ Updated with 18 additions and 4 removals
● Update(app/layout.tsx)
⎿ Updated with 6 additions
● Bash(npm run build)
⎿ ✓ compiled successfully in 4.2s
… +12 lines (ctrl+o to expand)
✻ Crunching… (2m 14s · ↓ 3.1k tokens)
> make the header stick to the top
⏵⏵ auto mode on (shift+tab to cycle)
api+On
✕+
› add a plan tiers table
• Ran npx supabase migration new plan_tiers
└ Created migrations/0007_plan_tiers.sql
Would you like to run the following command?
$ npx supabase db push
› 1. Yes, proceed
2. Yes, and don't ask again for this command
3. No, and tell Codex what to do differently
Press enter to confirm or esc to cancel
payments+86%On
2✕✕+
● Read(app/checkout/route.ts)
⎿ Read 214 lines
● Bash(npm test -- checkout)
⎿ ✓ 24 passed, 0 failed (6.1s)
… +31 lines (ctrl+o to expand)
✢ Deliberating… (3m 08s · esc to interrupt)
⎿ Tip: use /btw to ask a side question
> now handle the refund case too
⏵⏵ accept edits on (shift+tab to cycle)
docs+On
1✕+
● Done:
- pricing/page.tsx - added the yearly plan
- faq.tsx - answered the refund question
Next:
- read it over and tell me what to cut
✓ Committed 2 files
✻ Worked for 4m 12s · done 9:04 PM
> ▊
⏵⏵ auto mode on (shift+tab to cycle)
BoostsResearchAuditTaskReposGapsCompareValidate Edit
Ask Anna about your projects or send context to a chat Talk to Anna
Claude Daily 42%
Claude Weekly 61%
Codex Daily 18%
Codex Weekly 33%