For Claude Code, Codex, Cursor and Gemini CLI

Your AI agent,
finally in sight.

Olo lives in a corner of your screen. It shows you what your agent is doing, asks before anything important (on your phone too) and remembers what you teach it.

Olomni is the presence, approval and memory layer for AI coding agents. It runs on Mac and Windows, installs with one command and is free during the beta.

Works with

Your agent already works for you. The problem is you can’t see it, it asks when you’ve stopped looking, and tomorrow it has forgotten everything.

34 seconds

Watch it work.

From install to your first “yes” from the phone. No marketing cuts: this is the real Olo.

Olo grows with you

Meet Olo.

The face of your AI team. It sleeps, thinks, works and raises its hand when it needs you. And it grows with you: every task your AIs finish adds up, levels it up and earns it something to wear.

  • 🏅 Laurelfirst 100 only
  • 🌸 Floweryour first task
  • 🎧 Headphones3 days in a row
  • 👑 Crown14 days in a row
  • 📸 Your daya card to share

A day with your agent

Rests when there’s nothing to do.

No notifications, no noise. It just sits there, in its corner.

Works where you can see it.

While your agent moves forward, you know at a glance. Without opening a window.

Asks before what matters.

Publish, delete, deploy: it asks you, right here, and waits for your answer.

And remembers tomorrow.

What you teach one agent, the next one knows. Even if you switch tools.

Everything your agent
was missing.

Presence

A face that changes with what’s happening.

Sleeping, thinking, working, done. You know where your agent is just by glancing at the corner of your screen, even over full-screen apps.

Any agent

Whichever one you use.

It works with the agents you already have and connects them for you. Olomni doesn’t replace your agent: it lends it a body.

Claude CodeCodexCursorGemini CLI+ 4 via MCP

Shared memory

What one learns, they all know.

Your AIs save what’s worth remembering. You see every item and confirm, fix or delete it. Nothing is stored behind your back.

Approvals

You approve. Always.

Nothing important happens without your yes, on desktop or on your phone. And anything that could get expensive isn’t even asked: it’s blocked.

Agent handoff

Switch AIs without explaining everything again.

When an AI finishes, Olo notes where it left off. Open Codex in the project Claude Code just worked on, and Codex already knows. The handoff lives on your computer, with keys and tokens redacted.

Use cases

Built for how you work
with AI today.

Olomni doesn’t change your tools. It changes what happens while they work.

  1. Let it run and walk away.

    Long Claude Code or Codex tasks without babysitting the terminal. If it needs your permission, it reaches your phone and you decide with one tap, wherever you are.

    Claude Code asks · on your phone
  2. Several AIs at once, one Olo.

    Claude Code on the backend, Cursor on the frontend: each session gets its own lane and Olo points at the one waiting for you. Subagents show up as mini-Olos.

    2 working · 1 waiting for you
  3. Switch AIs without repeating context.

    You hit one tool’s limit or want a second opinion: the next AI starts knowing where the project was left.

    Handoff: Claude Code → Codex
  4. Production, with a safety net.

    Force pushes, deploys, deleting data: anything irreversible waits for your yes. If you trust something, choose “don’t ask again in this project”.

    git push --force · high risk
  5. Your day, on one card.

    Olo remembers what your AIs finished today. Copy the summary for your standup or share it.

    Today: 7 tasks done

You decide

Nothing important without your yes.

Your agent can do a lot. Olomni makes sure the irreversible goes through you first. Even when you’re away from your computer: the question reaches your phone.

Try it

Codex asks for permission Delete 1,240 inactive customers from the database
High risk
RejectApprove

Your agent is waiting. Your call.

These aren’t even asked

Moving money
Buying or selling stocks
Changing access permissions

Blocked automatically, even if the agent says it’s no big deal. And Olomni never runs anything on its own: it only carries your decision.

Comparison

Working with agents,
with and without Olomni.

How working with AI agents changes with Olomni
SituationWithout OlomniWith Olomni
Knowing what your agent is doingGoing back to the terminal to check.A glance at the corner of your screen.
Approvals while you’re awayThe session sits waiting for hours.It reaches your phone; you decide with one tap.
Dangerous actionsApproving everything blindly, or --dangerously-skip-permissions.The irreversible needs your yes; moving money is blocked.
Switching from Claude Code to CodexExplaining everything again.It starts knowing where the project stands.
Several AIs at onceFive windows and guessing which one is waiting.One lane per session; Olo points at the one that needs you.
MemoryA different instructions file per tool.One shared memory you can see, fix and delete.

Under the hood

Simple on the outside.
Clear on the inside.

Olo listens to your agent through its own hooks and through MCP, the open standard for AI tools. Your code never leaves your computer.

  1. 01 · your agent

    Claude Code, Codex, Cursor…

    Reports each step through its hooks and asks for permission over MCP.

  2. 02 · your computer

    Olo

    Shows the status, stops the irreversible and keeps the handoff between AIs.

  3. 03 · your account

    Olomni

    Carries approvals and status to your devices and stores the shared memory.

  4. 04 · your phone

    The remote

    Pings you and you decide with one tap. No app store.

Stays on your computer

  • The text of your prompts when you write to your agent
  • Your code and the contents of your files
  • Your AI’s full responses
  • The handoff between AIs, with keys and tokens redacted

Goes to your Olomni account

  • Each session’s status, like “Editing payment.ts”
  • A numbers-only summary when done: files, commands, minutes
  • Permission requests: a short description of the action and your answer
  • Messages you send to your AI from your phone
  • Your AIs’ memories: you see, confirm or delete them
What it is
A desktop app with a character (Olo), a remote on your phone and a shared memory for your AI agents.
Full integration
Claude Code, Codex, Cursor and Gemini CLI. Live status, approvals and handoff.
Via MCP
VS Code (Copilot), Windsurf, OpenCode, Cline and any agent that speaks MCP over HTTP.
Systems
macOS 12 or later (Intel and Apple Silicon) · Windows 10 and 11. Linux soon.
Phone
Any iPhone or Android, at olomni.com/remote. No app store.
Install
One single-use command. It pairs and connects your agents by itself.
Updates
Automatic and cryptographically signed.
Price
Free during the beta. No card.

Get started

Ready in three minutes.

One command, no keys to copy. Olo installs, pairs with your account and connects to your agents by itself.

Step 1

Get your command.

Create your free account, open Devices and tap Generate my command. It’s yours alone and works once.

Step 2

Paste it and press Enter.

On Mac open Terminal (⌘ + space, “Terminal”). On Windows open PowerShell (Windows key, “PowerShell”). Paste, Enter, and wait a few seconds.

Step 3

Olo is with you.

It appears in a corner of your screen, connected to Claude Code, Codex, Cursor or Gemini CLI if you have them. Open a new session of your agent and watch it work.

Your agent isn’t on the list? Manual setup

Any agent that speaks MCP over HTTP can use Olo. In Olo’s panel, Other agent or manual setup gives you these same lines with your key already filled in, ready to copy.


          
Olo gives you the real key.

Private beta · 100 founders

The first 100 wear the laurel.

An accessory that will never come back, your founder number on Olo and on your card, and a direct line to the person building it. Free during the beta.

  • 🏅 Founder laurelforever, with your number
  • 💬 Direct linewhat you ask for goes into the plan
  • 🆓 Free in the betano card, Mac and Windows

Frequently asked questions.

What is Olomni?

Olomni is the presence, approval and memory layer for AI coding agents. Its desktop app, Olo, shows what your agent is doing, asks for your permission before irreversible actions (even from your phone) and keeps a memory shared by all your AIs.

Which AI agents does it work with?

Claude Code, Codex, Cursor and Gemini CLI have full integration: live status, approvals and handoff. VS Code with Copilot, Windsurf, OpenCode and Cline connect over MCP, as does any agent that speaks MCP over HTTP. Olomni doesn’t replace your agent: it lends it a body.

How do I approve Claude Code actions from my phone?

Open olomni.com/remote on your iPhone or Android, add it to your home screen and pair it with a code from your profile. When Claude Code, or any connected agent, asks for permission, you get a notification and decide with one tap. Sensitive actions take two taps, never by accident.

Does Olo do things on its own?

Never. Olo shows what your agent does and carries your answer back when it asks for permission. Your agent does the work, and nothing important happens without your yes. Moving money, trading stocks and changing access permissions are blocked without asking.

How do Claude Code and Codex share context?

In two ways. Handoff: when an AI finishes a task, Olo notes where it left off and the next one you open in that project gets it on start; it lives only on your computer. Memory: what your AIs save, like “this project uses pnpm”, all of them can read, and you confirm, fix or delete it.

What do I do when Claude Code hits its usage limit?

Olo notices right away, saves where the work was left and offers to continue with Codex, Gemini CLI or Cursor with the full context. On Mac it opens the other AI in the project folder with the handoff already typed; it never switches AIs unless you choose to.

How do I know what will happen before approving a git push --force?

The permission card doesn’t trust the AI’s own summary: Olo checks on your computer what would really happen, such as “would erase 3 commits on origin/main you don’t have locally” or how many files a reset --hard would lose. You decide with facts, from your phone too.

What data leaves my computer?

Your prompts, your code and your AI’s responses stay on your computer. Only what’s needed to notify you goes to your account: each session’s status, a numbers-only summary when done, permission requests, and memories, which you see and control.

Do I need to know how to code?

No. You paste one single-use command and Olo installs, pairs with your account and connects to your agents by itself. If your agent isn’t on the list, Olo gives you the setup ready to copy.

Does it work on Windows?

Yes, on Windows 10 and 11: in Devices choose Windows, copy your command and paste it into PowerShell. Linux is on the way. Phone approvals work on any iPhone or Android.

Why doesn’t Olo float on my phone like on my computer?

iPhone and Android don’t let an app float over other apps. So on your phone Olo is a remote: it tells you when your agent needs you and you decide with one tap.

What if I lose my phone or change computers?

Go to your profile and tap Revoke on that device. It stops working instantly. Then pair the new one with another code.

My computer won’t let me open Olo. What do I do?

It doesn’t happen with the install command: Mac and Windows only block what you download with a browser. If you downloaded it by hand, try to open it, then go to System Settings → Privacy & Security → Open Anyway. Devices has the step-by-step.

How much does Olomni cost?

Nothing during the beta: no card, on Mac and Windows. The first 100 also get the Founder laurel for Olo.

Give your agent
a body.

No card. For Mac and Windows; Linux very soon. Approvals from any phone.