pluto f5f688277f feat: integrate recognition engine into MQTT event pipeline ...

- Recognition pipeline runs between snapshot fetch and notification
- Checks recognition_enabled setting before running CLIP matching
- Known objects with quiet/suppress action skip Matrix notifications
- Vision description uses configurable backend (haiku/ollama/both)
- docker-compose.yml adds CLIP/Ollama env vars and data volume

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-07 17:23:54 -06:00

app

feat: integrate recognition engine into MQTT event pipeline

2026-03-07 17:23:54 -06:00

clip-service

feat: add CLIP embedding service sidecar for GPU machine

2026-03-07 17:17:42 -06:00

tests

feat: add recognition engine with CLIP matching and Ollama vision LLM

2026-03-07 17:17:49 -06:00

.env.example

Initial commit: frigate-notify application

2026-03-07 14:30:57 -06:00

.gitignore

feat: scaffold v2 with FastAPI, SQLite database, and project structure

2026-03-07 17:02:17 -06:00

docker-compose.yml

feat: integrate recognition engine into MQTT event pipeline

2026-03-07 17:23:54 -06:00

Dockerfile

feat: scaffold v2 with FastAPI, SQLite database, and project structure

2026-03-07 17:02:17 -06:00

S

Description

AI-powered Frigate NVR video alert service: MQTT -> Claude Vision -> Matrix

94 KiB

Languages

Python 75.3%

JavaScript 16.7%

CSS 5.9%

HTML 1.6%

Dockerfile 0.5%