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
Reflect MCP Server Implements Reflexion Paper for Persistent Coding Agent Memory
A developer implemented the Reflexion paper (Shinn et al., NeurIPS 2023) as an MCP server to give local coding agents persistent memory of their mistakes. The system uses regex-based pattern matching on error messages and stores lessons in SQLite with FTS5.
AgentRoom: Desktop app visualizes AI coding agents as pixel characters with session search
AgentRoom is a desktop app that turns Claude Code, Codex, and Gemini sessions into animated pixel characters in a virtual office, with full-text semantic search across all sessions. The repo includes a standalone Claude Code skill for searching past sessions from any conversation.
Claude Code Mastery: Open-source config system adds persistent memory and curated skills to Claude Code CLI
Claude Code Mastery is an open-source configuration system that adds persistent memory across sessions, smart lifecycle hooks, and 26+ curated skills to Claude Code CLI. It includes a 6-file Memory Bank per project, zero-config launcher, and cross-platform support.
yburn: Tool to audit and replace unnecessary AI agent cron jobs
yburn is a Python tool that audits AI agent cron jobs and replaces those that don't need LLMs with standalone Python scripts. The creator found 58% of 98 cron jobs were purely mechanical tasks like system health checks and git backups.