Skip to content

HealthOS

HealthOS is a memory layer for a distributed individual health records in India.

Code Video Cerebral Valley

Core trick

Background agents build a layered patient memory graph from visit records, with Gemma fallback when offline.

Tags

healthagents

Description

HealthOS is a memory layer for a distributed individual health records in India. It provides an intutive UI for users to record there medical history and promptly runs the Agents in the background to build a three layer hierarchial memory structure continuously using gemini models and actively uses it in between the conversation of you and your doctor. It does not give diagnosis but it gives you a unforgettable memory which helps both patients and doctors. The App falls back to gemma models when internet is not available so that we can server people in low internet areas.
adityajha2007/maverick★ 00 forksTypeScriptCreated Jul 11, 2026 · last push Jul 11, 2026

README excerpt

# healthOS

An **AI Medical Memory** that lives on the patient's phone. Instead of storing documents like an EHR does, it stores relationships and longitudinal context in a per-patient Health Knowledge Graph — then lets an on-device multi-agent system observe, reason, and defer to a human when uncertain. Patients can chat with their memory in natural language, record a doctor visit in one language and share the translated brief in another, and hand a doctor a one-page summary via a shareable short URL and QR code.

Built for the **Google DeepMind Bangalore Hackathon** — targeting Track 1 (Local-First Agents on Gemma) with hybrid support for Track 2 (Gemini Live API) and Track 3 flavor (multi-agent orchestration).

## Status

- Backend: **14 pytest passing** (FastAPI + Gemma via `google-generativeai` + `google-genai` for Live API).
- App: **14 jest passing**, **0 TypeScript errors introduced** across all build phases (Expo SDK 57 + React Native + on-device Gemma 4 via MediaPipe LLM Inference).
- Runtime demo: **pending an Android device or emulator + Google AI Studio API key + Upstash Redis instance**. Every step is documented in `SETUP.md`.

## Read next

- **[`SETUP.md`](./SETUP.md)** — full onboarding guide. Prerequisites, backend + app setup, running end-to-end, testing, deployment sketches, troubleshooting. Includes §14 for the v0.2 architecture (multi-agent + Live API) and known runtime gaps.
- **[`DEMO_DRILL.md`](./DEMO_DRILL.md)** — demo-day pitch script (4-min primary

Team