One account, every screen: Raven on the web, desktop, and your phone
The same Raven, the same chats, everywhere you are: a full web app, native Windows and macOS apps, and Raven on Android and iPhone, syncing live across every screen.
Here is a boring sentence that will resonate with anyone who works for a living: your chats should not evaporate when you close a tab. Yet that is the deal with most AI tools. Tab closed, context gone, and the mobile app, where one exists at all, turns out to be a different and lesser product with its own confused idea of what your history is.
Raven takes the boring position that there is one product and you get it on every screen. The web app is complete: shared chats, research mode, connectors, documents, settings, everything. We held nothing back for a native upsell, because people who only ever use the browser deserve the whole thing, not a teaser.
Native where native matters
Native apps exist where native earns its keep. There is a Windows app for x64 and ARM64 machines, a macOS app for Apple silicon, and a phone app for Android and iPhone that installs like any other app. None of these is a "mobile edition" of the real product. The parking lot works exactly like the desk.
The sync is where it gets good
Start a question at your desk. Walk into a meeting. Finish typing it in the elevator, where the right phrasing always arrives late. Sit back down and the answer is already mid-stream on your screen.
That works because Raven keeps every signed-in device live through a realtime layer we built ourselves. Messages, shared-chat activity, even replies still in the middle of streaming show up on the other screens as they happen, not on the next reload. The industry default here is "refresh and pray", and we thought that was beneath the product. Give it a week and you stop thinking about which device has what. That, more than any individual app, is the feature.
Files, dark mode, and other luggage
Whatever you drop into a chat on one device, a file, an image, a screenshot, is waiting on the others by the time you switch. Midnight is no time for a bright white window. Dark mode follows you too.
Signing in
Google or Apple, once. The identity carries to the web, the desktop apps, and the phone. Your subscription, your usage, your memories, your connector settings, all of it rides on the account rather than the device. Configure nothing twice.
The desktop installers are on the download page, the phone app installs like any other app, and the web app is one click away. Whichever screen you pick, it is the same Raven looking back.
Get started
Try what we just shipped.
The real models, free in your browser, or download DCode and put them to work.
Related posts
DCode vs Cursor vs Copilot: why we side with the agent
Autocomplete, the AI-first editor, or the full agent: a straight comparison of the three philosophies of AI-assisted coding, written by the people who built the third one.
npm install and go: the DCode CLI and the real cost of the DipoleML API
The same Raven agent is one npm install away, and the API behind it publishes its price to the cent: $0.50 per 1M input tokens on Flash, credits that never expire, and per-key spend limits.
OpenAI gave up on plugins. We didn't give up on integrations.
ChatGPT plugins died in 2024, and the autopsy matters: sandboxed islands with no real account access were never going to work. Connectors, done properly, are the version that survives.