GlycemicGPT: Self-Hosted AI Diabetes Monitor with BYOAI and Plugin SDK
GlycemicGPT is an open-source diabetes management platform built for self-hosting. It connects continuous glucose monitors (CGM) and insulin pumps to an AI analysis layer that runs on your own infrastructure. The project was created by a Type 1 diabetic software engineer who needed a tool to review data between endocrinologist visits.
Supported Devices
- Dexcom G7 – via cloud API (verified)
- Tandem t:slim X2 – direct BLE + cloud API (verified)
- Tandem Mobi – BLE (protocol-compatible, not verified on physical hardware)
- Nightscout – point at your existing instance
AI Layer Features
- Daily briefs summarizing overnight and 24-hour patterns
- Meal response analysis
- Conversational chat backed by RAG with clinical knowledge
- Predictive alerting with configurable thresholds and caregiver escalation
Important: GlycemicGPT does not deliver insulin, control pumps, or function as a closed-loop system. It reads data and provides insights only.
Architecture
- Self-hosted via Docker or Kubernetes – runs entirely on your hardware
- BYOAI – bring your own AI provider: Ollama for fully local operation (zero data leaves your hardware), or any OpenAI-compatible endpoint (Claude, OpenAI, etc.)
- Data flows directly from your instance to the chosen provider; no centralized project-operated services
Stack
- 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, sandboxed
Quick Start
Deploy with Docker Compose, configure a .env file with your device credentials and AI provider endpoint, then run:docker compose up -d
You can point it at an existing Nightscout instance for immediate data ingestion.
Who It's For
Developers with diabetes who want to self-host their own AI-powered monitoring stack, and contributors interested in BLE/Android or diabetes device integrations.
📖 Read the full source: HN AI Agents
👀 See Also
Double-Buffering Technique for LLM Context Windows Eliminates Stop-the-World Compaction
A technique called double-buffering can prevent LLM agents from freezing during context window compaction by summarizing early and maintaining two buffers, allowing seamless handoff at no extra inference cost.
Community patch adds RTL language support to Claude Desktop on Windows
A developer has created a patch that adds proper right-to-left language support to Claude Desktop on Windows, fixing broken rendering for Hebrew, Arabic, and other RTL languages. The patch injects RTL detection logic into the Electron app's renderer and includes backup/restore functionality.
Claude Code Memory Leak Fix for Linux Homelabs
A developer discovered Claude Code has a severe memory leak in glibc malloc that consumed 400GB RAM and crashed their Proxmox homelab, then created a two-tier guard solution with LD_PRELOAD shim and watchdog.
OpenClaw as Infrastructure-as-Code Interface for Home Lab Management
OpenClaw transforms from AI gadget to primary computer interface for home lab management, executing tasks like configuring Traefik containers, creating Dashy configurations, and setting up Tailscale access with direct machine access.