GlycemicGPT
Open-source AI-powered diabetes management
Details
- External ID
- 48144670
- Source
- HN
- Company
- —
- Product
- GlycemicGPT
- Website domain
- github.com
- Launched
- May 15, 2026
- Cohort
- —
- Upvotes
- 64
- Upvotes percentile
- 0.8618739903069467
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I'm a Type 1 diabetic and software engineer. Last year I went months between endocrinologists with no clinician reviewing my data. I'm an engineer, so I built the tool I needed — and now I'm open sourcing it. GlycemicGPT is a self-hosted platform that connects continuous glucose monitors, insulin pumps, and existing Nightscout instances to an AI analysis layer running on your own infrastructure. Data sources:Dexcom G7 (cloud API) Tandem t:slim X2 and Mobi pumps (direct BLE) Nightscout (point it at your existing instance and you're running in minutes)What the AI layer does:Daily briefs summarizing overnight and 24-hour patterns Meal response analysis Conversational chat with RAG-backed clinical knowledge Predictive alerting with configurable thresholds and caregiver escalationImportant: this is monitoring and analysis only. GlycemicGPT does not deliver insulin, does not control your pump, and is not a closed-loop system. It reads your data and gives you insight on top of it. Your clinical decisions stay between you and your care team. Architecture:Self-hosted via Docker or K8S — the GlycemicGPT stack runs entirely on your hardware BYOAI — bring your own AI provider. Use Ollama for fully local operation (no data leaves your hardware), or point it at Claude, OpenAI, or any OpenAI-compatible endpoint if you prefer a hosted model. Data flows directly from your instance to the provider you choose; nothing is routed through any centralized service operated by the project. GPL-3.0, no subscriptions, no vendor lock-inStack:Backend API: FastAPI, Python 3.12, PostgreSQL 16, Redis 7 Web Dashboard: Next.js 15, React 19, Tailwind CSS, shadcn/ui AI Sidecar: TypeScript, Express, multi-provider proxy Android App: Kotlin, Jetpack Compose, BLE Wear OS: Kotlin, Wear Compose, Watch Face Push API Plugin SDK: Kotlin interfaces, capability-based, sandboxedLooking for contributors — especially folks with BLE/Android experience or anyone in the diabetes tech space. Plugin SDK is documented if you want to add support for new devices. GitHub: https://github.com/GlycemicGPT/GlycemicGPT
Enrichment
- Theme
- ai nutrition and meal tracking
- Vertical
- Healthcare
- Function
- Vertical SaaS
- Audience
- B2C
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- ai-powered diabetes management platform
- Manually corrected
- False
Could you build this?
Partial Building the web dashboard and querying an LLM with glucose logs is straightforward, but reverse-engineering and reliably integrating proprietary medical hardware protocols (Dexcom, Abbott Freestyle Libre, insulin pumps) while managing clinical risks requires non-trivial domain expertise.
What it would actually take: The architecture involves an ingestion service connecting to Nightscout APIs, Dexcom Share APIs, or Bluetooth Low Energy (BLE) transmissions from continuous glucose monitors, paired with a time-series database (e.g., InfluxDB/TimescaleDB) and a Next.js web application. The core hard parts are reverse-engineering undocumented continuous glucose monitoring protocols, managing real-time Bluetooth telemetry syncing, and formatting sensitive medical time-series data accurately for LLM context windows without hallucinatory dosage recommendations. It requires familiarity with diabetes protocols, BLE GATT profiles, and health data compliance.
Discussion
20 comments analyzed.
Competitors mentioned: Dexcom CGM, Freestyle Libre CGM, AAPS (AndroidAPS), ChatGPT for diabetes information
Concerns raised: LLM hallucinations providing dangerous medical advice, Unregulated unlicensed tool giving medical guidance to consumers, Risk of false low glucose readings leading to insulin dosing errors, Requires clinician involvement but unclear how to enforce that, System failure modes (refused responses, malformed data) not addressed
Feature requests: Prompt users to log meals/exercise with contextual reminders, Detect behavior changes and ask follow-up questions to understand patterns, Mechanism for users to flag incorrect AI outputs for retraining, Integration with sleep and other health device data, Easy time-aligned data visualization for patient-clinician discussions
Competitors
Other products that read as similar to this one — 31 launches clear the similarity bar, closest 8 shown.
Attention rank: #7 of 32 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 90 days after the earliest competitor.
- GLP AI · ph · 2026-09-30 · 1 upvotes · similarity 0.48
- Glux · ph · 2026-09-20 · 2 upvotes · similarity 0.43
- GLIP · ph · 2026-09-23 · 1 upvotes · similarity 0.43
- 💉 🩸SiPhox Health GLP Monitoring · yc · 2026-06-03 · 31 upvotes · similarity 0.43
- t1-arc · github · 2026-09-17 · 12 upvotes · similarity 0.43
- Pinwise · ph · 2026-09-23 · 1 upvotes · similarity 0.42
- Peptimize · ph · 2026-09-18 · 5 upvotes · similarity 0.40
- Sugar Sense · ph · 2026-09-15 · 3 upvotes · similarity 0.40
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a vertical saas tool for Insurance yet.