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
mycrab.space introduces SKILL.md and Prompt Autocomposer for standardized app deployment
mycrab.space has released SKILL.md, a Markdown blueprint for defining app dependencies and configuration, and a Prompt Autocomposer that generates ready-to-use deployment commands from these files. The system enables zero-config deployment of applications like VS Code in browser, personal music clouds, and AI agent interfaces.
RelayCode VS Code Extension Routes Claude Code Through Sovereign RDUs
OpenGPU has released RelayCode, a VS Code extension that acts as a local proxy to route Claude Code or Copilot requests through their decentralized network to open-weight models like DeepSeek-R1 and MiniMax M2.5 running on sovereign reconfigurable dataflow units.
CSS Modern Features Agent Skill: Enforce Modern CSS Practices in AI Coding Agents
An agent skill that enforces 57+ modern CSS features across color, layout, selectors, animation, typography, positioning, and component patterns, compatible with Claude Code, Cursor, Windsurf, Codex, Cline, and GitHub Copilot.
Claude Command Center: Open-Source Dashboard for Claude Code Analytics
Claude Command Center is a local dashboard that reads your ~/.claude/ directory to display Claude Code session data, costs, and MCP server configurations. Built entirely using Claude Code with an Express backend and React frontend, it requires zero configuration and runs locally with no cloud or telemetry.