See what your AI is actually doing

Agent Deck runs the AI coding tools you already pay for, in one place on your own computer. Bring your own Claude, Codex, Copilot, Gemini, and OpenCode accounts. See what each one plans to do, run it in a safe space, and keep every chat on a machine you own.

The AI-native code editor that gets it exactly right. No approximation. No bloat. Just perfect code, every time.

Built by engineers at

Fortune 500 enterprises and studios.

//

Core features

Your dev brain.
Structured and reusable.

One workspace for every AI you use

Use Claude, Codex, Copilot, Gemini, and OpenCode side by side. Every chat is saved on your own computer. Hit a limit on Claude in the middle of a task? Move the chat to Codex and keep going. You never lose your place.

One workspace for every AI you use

Use Claude, Codex, Copilot, Gemini, and OpenCode side by side. Every chat is saved on your own computer. Hit a limit on Claude in the middle of a task? Move the chat to Codex and keep going. You never lose your place.

Bring your own AI.

Connect the Claude, Codex, Copilot, and Gemini accounts you already pay for. Agent Deck does not include AI usage or resell it. You pay your providers directly, at their price.

Bring your own AI.

Connect the Claude, Codex, Copilot, and Gemini accounts you already pay for. Agent Deck does not include AI usage or resell it. You pay your providers directly, at their price.

An AI that already knows your project

Agent Deck reads your code and writes simple notes about each part. What it does. How it connects. Every new chat starts with those notes already loaded. Other tools just scan your files and guess. Yours starts with a real map, so you stop explaining the same project over and over.

Works with what you already use.

Claude, Codex, Copilot, Gemini, OpenCode. Keep your current tools and plans. No need to switch.

Works with what you already use.

Claude, Codex, Copilot, Gemini, OpenCode. Keep your current tools and plans. No need to switch.

//

Use cases

One runtime. Every workflow.

  • One place. Every AI.

    Run Claude, Codex, Copilot, Gemini, and OpenCode from one workspace. Every chat is saved in a database on your own computer. Hit a limit on Claude in the middle of a task? Move the chat to Codex and keep going. Nothing gets lost.

  • Safe by default.

    Every AI action runs inside a sealed box. Agent Deck turns your request into a plan and shows you what the AI wants to do. Then it runs that work in a closed space. Let the AI try risky things. Your computer and your files stay safe.

  • AI that knows your project.

    Agent Deck reads your code and writes plain notes about every part. What it does. How it connects. Every AI chat starts with those notes already loaded. Most tools just scan your files and guess. Yours starts with a real map. You stop re-explaining the same project every session.

  • Spend with intent.

    Agent Deck lets you set a limit before the AI spends. Set the cap per AI, per project, or per chat. The AI stops when it hits the limit. You set the guardrails up front instead of getting a surprise bill later.

Multi-provider chats

Sandboxed agents

RAG indexing

Budget gating

One place. Every AI.

Run Claude, Codex, Copilot, Gemini, and OpenCode from one workspace. Every chat is saved in a database on your own computer. Hit a limit on Claude in the middle of a task? Move the chat to Codex and keep going. Nothing gets lost.

//

Benefits

Why people pick Agent Deck.

Runs on your machine.

Your code, chats, and notes stay on your computer. Nothing gets sent to an outside cloud.

No extra markup.

You connect your own AI accounts. Agent Deck does not resell access or add a fee on top. You pay for what you use.

Nothing gets forgotten.

Your chats, choices, and project notes survive restarts, limits, and tool switches.

Your chats stay yours.

Every chat is saved on your computer. Move them, copy them, or delete them. Your call.

Try things safely.

Every action runs in a safe box first. Let the AI try the risky thing. If it breaks, your computer does not.

Experiment without breaking things.

Every action runs inside a safe box. Try the risky thing. If it breaks, your computer doesn't.

//

Pricing

Pay once for the runtime.
Add cloud as you need it.

Waitlist

$25

one-time

For early users. All core features included.

Features

Unlimited local projects

AI autocomplete (basic)

Code chat assistant

50+ languages support

Terminal integration

Runtime

Popular

$30

$30

one-time

The full local runtime with advanced features. One simple price.

Features

Multi-provider chats (Claude, Codex, Copilot, Gemini, OpenCode)

Automated sandboxing

RAG indexing and auto-docs

Token budgeting and cost gating

Local SQLite chat store

Export and import across providers

Agent Pro

$15-25/mo

For teams that need support, custom setup, and stronger security.

Features

Everything in Runtime

Chat search (try 30 days free)

ChatSync across devices and team (mobile coming soon)

Cost Sync (shared team budgets and visibility)

SSO and SAML

Self-hosted deployment

Custom AI model training

Waitlist

$25

one-time

For early users. All core features included.

Features

Unlimited local projects

AI autocomplete (basic)

Code chat assistant

50+ languages support

Terminal integration

Runtime

Popular

$30

$30

one-time

The full local runtime with advanced features. One simple price.

Features

Multi-provider chats (Claude, Codex, Copilot, Gemini, OpenCode)

Automated sandboxing

RAG indexing and auto-docs

Token budgeting and cost gating

Local SQLite chat store

Export and import across providers

Agent Pro

$15-25/mo

For teams that need support, custom setup, and stronger security.

Features

Everything in Runtime

Chat search (try 30 days free)

ChatSync across devices and team (mobile coming soon)

Cost Sync (shared team budgets and visibility)

SSO and SAML

Self-hosted deployment

Custom AI model training

Waitlist

$25

one-time

For early users. All core features included.

Features

Unlimited local projects

AI autocomplete (basic)

Code chat assistant

50+ languages support

Terminal integration

Runtime

Popular

$30

$30

one-time

The full local runtime with advanced features. One simple price.

Features

Multi-provider chats (Claude, Codex, Copilot, Gemini, OpenCode)

Automated sandboxing

RAG indexing and auto-docs

Token budgeting and cost gating

Local SQLite chat store

Export and import across providers

Agent Pro

$15-25/mo

For teams that need support, custom setup, and stronger security.

Features

Everything in Runtime

Chat search (try 30 days free)

ChatSync across devices and team (mobile coming soon)

Cost Sync (shared team budgets and visibility)

SSO and SAML

Self-hosted deployment

Custom AI model training

//

FAQ

Questions? We've got answers.

Do I need my own AI subscriptions?

Does Agent Deck replace Claude or Copilot?

Which AI tools work with it?

What runs on my computer, and what runs in the cloud?

How does the safe box work?

Does it work without internet?

What if I want to share with others?

Own your AI context. Starting now.

Join the paid waitlist for $25. Lock in lifetime discounts on every cloud tier, plus first access to the runtime when it ships.