Your COO. In an app.
The AI that runs your day — from morning brief to nightly wrap-up. Native on Mac, iPhone, iPad, and Apple Watch.
Requires macOS 26 or later • Apple Silicon • Free • Private beta — access code required
Hit something weird? Found a bug? Tell us — we read every one.
From the terminal on your Mac to a glanceable brief on your Watch — Claudine moves with you.
Available on iPad — $1/mo
Claudine doesn't wait to be asked. It tracks context, surfaces blockers, and gets things done.
Wake up to your day already planned — priorities, calendar, overnight messages.
Resume any project exactly where you left off. No re-explaining, no setup.
Action items captured and scheduled automatically. Walk in briefed, leave with nothing missed.
Triage bugs, review PRs, fix tests — from the same interface that manages your day.
Mac, iPhone, iPad, Apple Watch. One context, everywhere you are.
Powered by Claude CLI. Your Mac does the work.
No subscriptions to manage your Mac. A small one to extend to your phone.
The full Claudine experience, natively on Mac.
Your context, on iPhone and Apple Watch.
| Platform | macOS (free) • iOS • watchOS ($1/mo) |
| macOS | macOS 26 Tahoe or later |
| Chip | Apple Silicon (M1 or later) |
| iOS | iOS 19 or later |
| watchOS | watchOS 12 or later |
| Distribution | macOS: direct download (notarized) • iOS: TestFlight beta |
macOS distributed as a notarized direct download — no App Store required. Independent product. Not affiliated with Anthropic, OpenAI, or Google.
Claudine is powerful the way a motorcycle is powerful. There are no seatbelts here, on purpose.
Point it at your brokerage and it can trade your account to zero. Aim it at your bank and it can move money you won't get back. The first night we wired up a prediction market — Super Bowl night — a bug lost $500 in seconds. That's not a horror story we're hiding; it's the honest shape of the thing.
Claudine is not a financial advisor, a broker, or a fiduciary, and nothing it does is advice. Anything it touches — money, trades, your business — happens at your direction and your risk. You hold the throttle. You own the outcome, including the expensive ones.
This is for people with the means and the stomach to make it to the other side. If that's not you yet, that's fine — start small, ramp slowly, and never delegate more than you can afford to be wrong about.
Be clear-eyed about what this is: Claudine's current workflow runs on the Claude command-line tool. That is the engine today. When Claude's service is degraded or down, Claudine is degraded or down with it — there is no separate cloud we keep running in its place. Multi-model support (Codex, Gemini, and on-device models) is on the roadmap and will soften this, but right now the dependency is real and singular.
This technology is maturing in real time. Providers ship breaking changes, move rate limits, and larger forces are in play — a release pulled, a frontier model restricted by a government, an account throttled without warning. Any of these can take the app offline for a stretch, through no fault of your own setup.
So expect some disruption. The AI providers are nowhere near the "five nines" (99.999%) uptime you'd assume from mature infrastructure — they are research labs and startups operating at the frontier, not utilities. We build for resilience and we keep widening the set of models you can fall back to, but we won't pretend the ground is steadier than it is.
This is the same honesty we bring to everything: name the risk plainly, then let you decide. The risks are real. The rewards are real.
Read the full philosophy