Your phone remembers your work. Point the camera, say one line, ask it anything later. Nothing leaves the device.

Site engineers, shop owners, lab technicians, field staff: people whose work doesn't happen at a desk and who will never type notes. Smriti lets them press once, capture the thing in front of them, say one line about it, and later ask out loud. The answer comes back with the original photo as evidence.
The Latin OCR model returns near-empty text on Devanagari. Smriti runs both recognisers and keeps whichever read more.
So the extractor never throws: it repairs braces, fences and trailing commas, aliases keys, retries once, then falls back to the raw transcript. Losing a capture is the worst failure.
On a stock Moto G05 the recogniser had no language pack. That made on-device Whisper a requirement for the offline build, not a stretch goal.
MediaPipe's GPU backend segfaults on Mali mid-generation. A sentinel quarantines the GPU after one unexplained death.
A telemetry library silently added INTERNET through the manifest merger. A build task now fails if the shipping manifest ever asks for network.
One shutter: tap for photo, hold for photo + voice, mic for voice only. No forms.
Every answer shows the source record and its photo, because a 1B model has to show its working.
[ on-device ], [ 9 memories ], [ fri, sep 4 ]: small bracketed tags carry state without adding chrome.
Crops from the Smriti Figma file, then the real app on a real phone.







Selected as a finalist at the iQOO Hackathon 2026. The offline build ships with no network permission at all, and a build-time guard makes sure it stays that way.