martin888/yunkan repository overview

⁠YunKan (云瞰) — self-hosted AI NVR / VMS, all in one container

Privacy-first home & small-business camera recording + on-device AI. Your video never leaves your LAN — nothing is uploaded to any vendor cloud, and AI inference (people / vehicles / faces / license plates / pose / fall) runs entirely on-box, no OpenAI / Gemini / Claude API key required.

A self-hosted alternative to Frigate / Shinobi / ZoneMinder / Scrypted / Agent DVR / iSpy / MotionEye / BlueIris — but pre-bundled into a single container (ZLMediaKit + database + recording + detection + web admin + nginx, supervised by s6-overlay): no Mosquitto / DB / reverse-proxy / model-download wiring to do by hand.

This is the CPU build (martin888/yunkan = martin888/yunkan-cpu) — runs on any amd64 host, no special hardware. Intel iGPU? use martin888/yunkan-openvino (3–5× faster). NVIDIA GPU? use martin888/yunkan-cuda. Tags: latest and pinned (e.g. 0.9.9). Only one variant runs at a time (shared ports).

⁠Features

• 24/7 continuous recording + motion-event highlights, scrubbable timeline playback.
• On-device AI: person / vehicle / pet / face recognition / license plate (ALPR) / pose & fall detection / gesture / cry detection — all local.
• AI scene understanding: each event gets a natural-language summary (e.g. "an elderly person fell in the living room") + semantic event search.
• Sub-second live via WebRTC (WHEP) with HLS fallback; live detection-box overlay.
• Two-way talkback, Home Assistant MQTT auto-discovery, Web admin + Android + iOS apps, optional 115 Cloud off-site backup.
• Works with any RTSP / ONVIF camera (Reolink, Hikvision, Dahua, Amcrest, Annke, Uniview, EZVIZ, Foscam, Lorex…); Tapo / Wyze / Xiaomi / Eufy / Aqara / Imou via a go2rtc bridge.

⁠Quick start (recommended: one-line installer)

The installer auto-detects your hardware, picks the right variant, randomizes the JWT secret, and sets up the OTA self-update sidecar:

curl -fsSL https://cdn.yun-kan.com/yunkan-install.sh | bash

Then open http://:23406/, run the setup wizard (pick SQLite for the simplest path), create an admin, add cameras.

⁠Manual docker compose (CPU)

Save as compose.yml then docker compose up -d:

name: yunkan                       # fixed project name (kept stable across upgrades)

services:
  yunkan:
    image: martin888/yunkan-cpu:0.9.9   # or :latest
    container_name: yunkan
    restart: always
    network_mode: host             # WebRTC ICE / RTSP / HLS need many ports
    volumes:
      - ./data:/app/data                       # DB / logs / cookies / upgrade state
      - ./recordings:/app/data/recordings      # recordings (point at a big disk / NAS)
      - /etc/machine-id:/etc/machine-id:ro                       # license HW fingerprint
      - /sys/class/dmi/id/product_uuid:/sys/class/dmi/id/product_uuid:ro
      - /var/run/docker.sock:/var/run/docker.sock                # in-app OTA upgrades
    environment:
      - TZ=Asia/Shanghai
      - SKYVIEW_SELF_CONTAINER_NAME=yunkan

⁠Ports (host networking)

Public / WAN: set SKYVIEW_WEBRTC_EXTERN_IPS=<public-ip-or-domain> so WebRTC ICE candidates are reachable.

⁠Links

• 🌐 Website & docs: https://yun-kan.com⁠
• 📝 Changelog: https://yun-kan.com/changelog⁠

Keywords: NVR, VMS, CCTV, surveillance, IP camera, RTSP, ONVIF, person detection, vehicle detection, face recognition, license plate recognition, ALPR, fall detection, two-way audio, talkback, 24/7 recording, timeline playback, WebRTC, HLS, Home Assistant, MQTT, AI NVR, on-device AI, edge AI, no cloud, privacy, self-hosted, Frigate alternative, 云瞰, 摄像头, 监控, 本地 AI.