Aaron D. Lee a5ddc53cf0 feat(S3): FaceRecognizer with in-memory embedding matching ...

Add FaceRecognizer class that loads face encodings from the database,
supports runtime add_encoding(), and matches new encodings by L2 distance.
face_recognition import is deferred so the class works without dlib installed.
FaceResult dataclass carries profile_id, name, confidence, crop, and bbox.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-03 18:59:07 -04:00

config

Initial commit: Vigilar DIY home security system

2026-04-02 23:11:27 -04:00

docs

Add visitor recognition design spec (S3)

2026-04-03 15:32:12 -04:00

kiosk

Add kiosk setup and deployment scripts (Phases 5 + 9)

2026-04-02 23:25:03 -04:00

remote

Initial commit: Vigilar DIY home security system

2026-04-02 23:11:27 -04:00

scripts

Add presence detection, person/vehicle AI detection, health monitoring

2026-04-03 00:06:45 -04:00

systemd

Add kiosk setup and deployment scripts (Phases 5 + 9)

2026-04-02 23:25:03 -04:00

tests

feat(S3): FaceRecognizer with in-memory embedding matching

2026-04-03 18:59:07 -04:00

vigilar

feat(S3): FaceRecognizer with in-memory embedding matching

2026-04-03 18:59:07 -04:00

.gitignore

Add .worktrees/ and .superpowers/ to .gitignore

2026-04-03 13:02:10 -04:00

.python-version

Fix lint issues in pet detection integration

2026-04-03 13:32:17 -04:00

CLAUDE.md

Initial commit: Vigilar DIY home security system

2026-04-02 23:11:27 -04:00

pyproject.toml

feat(S3): visitor event types, VisitorsConfig, face_recognition dependency

2026-04-03 18:56:55 -04:00

requirements-dev.txt

Initial commit: Vigilar DIY home security system

2026-04-02 23:11:27 -04:00

requirements.txt

Initial commit: Vigilar DIY home security system

2026-04-02 23:11:27 -04:00

Description

Local AI-model assisted home security and surveillance system for those that don't trust that data to the cloud.

851 KiB

Languages

Python 63.7%

HTML 21.6%

Shell 8.2%

JavaScript 5.5%

CSS 1%