# zapdos-labs/unblink

Camera monitoring with VLM

Repository: https://github.com/zapdos-labs/unblink
Canonical: https://ross.abutalabs.com/products/unblink
Language: Go
License: AGPL-3.0
License Family: copyleft
Topics: camera, computer-vision, monitoring, nvr, vlm
Last push: 2026-03-09T09:42:25+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 40, longevity 21
- inputs: {"age_days": 301, "days_push": 177, "days_rel": 184, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1501, forks 169 (observed 2026-08-28T04:04:54.321264+00:00)

## What it is
Unblink is an AI-powered camera monitoring application that uses a vision language model (Qwen3-VL) to analyze camera frames, summarize activity, and enable natural-language chat and search over recorded video. It uses a relay-node architecture where a local node proxies RTSP/MJPEG camera streams to a publicly reachable server, with a SolidJS frontend and PostgreSQL storage.

## Use cases
- monitor my home security cameras with AI
- search recorded camera footage using natural language
- chat with an assistant about what my cameras saw
- self-hosted NVR with vision language model analysis
- summarize camera activity automatically
- view RTSP cameras remotely through a relay
- get alerts describing what happened on camera

## When to choose
- you want AI/VLM-based analysis and natural-language search over camera feeds
- you need a self-hosted NVR with remote access via relay nodes
- you have RTSP or MJPEG cameras and want frame-level semantic understanding
- you prefer a Go-based, deployable-to-cloud monitoring stack

## When to avoid
- you need a lightweight NVR without AI features or LLM costs
- you require support for camera protocols beyond RTSP/MJPEG
- you need a fully offline solution without a relay server
- AGPL-3.0 licensing is incompatible with your usage

## Facets
- artifact type: application
- maturity: active
- function: computer-vision, video-processing, monitoring, search-engine, chatbot, llm-inference, streaming
- domain: computer-vision, security, self-hosted, artificial-intelligence, monitoring
- platform: windows, cross-platform, self-hosted
- tags: nvr, vlm, rtsp, webrtc, camera-monitoring, video-search, solidjs, go2rtc, relay-node, video, linux, macos, web-server, docker

## Member repositories
- zapdos-labs/unblink (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.321264+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:58.127298+00:00, confidence not recorded.
  - readme: https://github.com/zapdos-labs/unblink (fetched 2026-08-28T04:04:54.321264+00:00, sha 70e8add0309c)
- Data as of 2026-08-30T08:39:29.467469+00:00.