Launching today
Attyn brings intelligence to the cursor inside the apps you already use. Rewrite selected text with Inline Assist, speak finished words with Realtime Dictation, ask about what is on screen with Screen Assist, and turn questions into visual explanations with Blackboard. Use Attyn Credits, bring a provider key, or run a supported local model. Attyn is bootstrapped and independent. Available for macOS today, with Windows on the way. Every new account starts with 500 launch credits.
Attyn
Attyn
Watch Attyn in action:
Complete product film: https://youtu.be/0qGNmaA9gDg
30-second tour: https://youtu.be/66BQUMIi7CU
@Rohit C — the local-model/BYOK choice is a strong complement to cursor-level assistance. Screen Assist plus Blackboard looks especially useful when a question needs both the current app context and a visual explanation. How are you deciding when Attyn should infer context automatically versus ask the user to scope what it can see?
Attyn
@getosmo Thanks Anuj. The line we drew is simple: attyn infers the cheap, harmless context on its own, and a deliberate gesture from you is what grants the sensitive kind.
Inferred automatically: which app is frontmost, where your cursor is.
Content is always scoped by the gesture itself. Inline Assist sees only the text you selected. Screen Assist sees the screen only at the moment you tap the shortcut, and if you hold it instead, you circle exactly the region it may look at. Nothing is watched passively between gestures, and captures exclude attyn's own windows.
So there's no runtime heuristic deciding what to read. The gesture is the consent.