oliverbravery/PrintGuard

Catches failed 3D prints on your own hardware, pauses the printer and sends you a snapshot alert. Runs in your browser with nothing to install, in Docker, or as a macOS or Windows app. Free and open source, and no frame ever leaves your network.

What it solves

PrintGuard prevents wasted material and potential hardware damage by automatically detecting failed 3D prints (such as "spaghetti" failures) in real-time. It eliminates the need for constant manual monitoring or expensive cloud subscriptions by running the detection locally on the user's own hardware.

How it works

The system uses a compact vision model (based on a ShuffleNetV2 encoder) that scores camera frames for defects. When a defect is detected and persists for a set duration, PrintGuard triggers an action via the printer's server—such as pausing or cancelling the print—and sends a snapshot alert to the user's phone. It can run in "Local mode" (directly in a web browser via WASM) or "Hub mode" (as a standalone server/Docker container) and supports various hardware acceleration providers like Core ML, TensorRT, and OpenVINO to optimize performance.

Who it’s for

3D printing enthusiasts who use FDM printers and want an automated, privacy-focused way to monitor their prints without relying on cloud services.

Highlights

  • Broad Compatibility: Supports OctoPrint, Klipper, Elegoo, Prusa, and Bambu Lab printers.
  • Local Processing: Camera frames never leave the user's hardware, ensuring privacy and no subscription fees.
  • High Performance: Optimized for edge devices, achieving significantly higher throughput and accuracy than competing open models on Raspberry Pi hardware.
  • Flexible Alerts: Integrates with ntfy, Pushover, Telegram, and Discord.
  • Extensible: Includes a plugin system for adding custom functionality and an API/MCP server for automation.

Related

  • Project
    QuinnDamerell/OctoPrint-OctoEverywhere

    A remote access and monitoring service for 3D printers that includes AI-powered print failure detection to automatically stop failed prints.

  • Project
    leptonai/gpud

    A production-grade GPU monitoring and management tool that ensures hardware efficiency and reliability for AI/ML workloads.

  • Dispatch
    Pollen-Vision: Unified Interface for Zero-Shot Vision Models in Robotics

    Hugging Face and the Pollen Robotics team have released pollen-vision, an open-source library that integrates zero-shot vision models to enable robots to detect and localize unknown objects in 3D space.

  • Dispatch
    ScreenMind: Local AI Screen Memory Powered by Gemma 4

    ScreenMind is an open-source, privacy-first alternative to Microsoft Recall that uses Gemma 4 E2B to locally capture, analyze, and search screen history on GPUs with as little as 4GB VRAM.

  • Project
    traceroot-ai/traceroot

    An open-source observability and self-improving layer for AI agents that detects production failures, root-causes them to source code, and opens verified fix PRs.