Run YOLO26 locally with OpenEye

    Latest generation YOLO model (YOLO11) optimized for speed. Smaller weights and faster inference than YOLOv8 with comparable accuracy. OpenEye, the open-source perception CLI, downloads YOLO26, runs it on your CPU or GPU, and returns structured JSON you can pipe into scripts, agents, and robots.

    TaskObject detection
    CLI idyolo26
    CreatorUltralytics
    Weightsultralytics/yolo11 (~5 MB)
    HardwareCPU, NVIDIA CUDA, Apple Silicon (MPS)
    Install extraopeneye-sh[yolo]

    1. Install

    pipx install "openeye-sh[yolo]"

    2. Pull YOLO26

    openeye pull yolo26

    3. Run inference

    Output is JSON on stdout, so it composes with jq and any other Unix tool.

    openeye run yolo26 photo.jpg --pretty

    4. Serve it as an API

    Start a local server with REST and WebSocket endpoints for apps, agents, and live camera streams.

    openeye serve yolo26

    See the serve reference, REST endpoints, and Python SDK.

    Other models