Commit Graph

2 Commits

Author SHA1 Message Date
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
Jeremy Hobbs 6086ed3cc0 Initial commit: frigate-notify application
AI-powered video alert service that bridges Frigate NVR events to Matrix.
Listens to MQTT, uses Claude Haiku vision to analyze snapshots, and posts
annotated alerts to a Matrix room.

- app/main.py: MQTT subscriber and event orchestration loop
- app/vision.py: Claude Haiku vision analysis wrapper
- app/matrix_client.py: Matrix HTTP client for sending messages/images
- app/requirements.txt: Python dependencies
- Dockerfile: container image build definition
- docker-compose.yml: deployment configuration (host network, NAS mounts)
- .env.example: required environment variable template (copy to .env)
2026-03-07 14:30:57 -06:00