SlopScore
00 crowd

argus

Self-hosted face and object recognition — REST API + browser UI in one container. Enroll people by name, review uncertain matches, detect objects. InsightFace + YOLO, GPU auto-detected, SQLite, no cloud.
Open repo on GitHub Open the demogithub.com/MichaelYagi/argus
Python · ★ 2 · 0 forks · MIT · paperwork by the Cap'mmostly ai (inferred)light human (inferred)works-on-my-machine (inferred)other
listed 1 hour ago by MichaelYagi · last checked 1 hour ago
The owner didn't write this. This repo never submitted itself. The Cap'm found it on a truffle trawl and wrote its paperwork from what GitHub already shows. Picked by hand by the Cap'm on 2026-10-10: Self-hosted face and object recognition — REST API + browser UI in one container. Enroll people by name, revie; its own README says "100% of the code was written by Claude (Anthropic); I shaped the architecture, scope, and every decision, and did all the testing". 2 stars; MIT license. The owner did not submit this. Votes count; awards don't until the owner claims it.

I'm not calling your project slop! Geeze, it's a joke... Do you own this repo?

Log in with GitHub as MichaelYagi. There's no account to make: SlopScore only asks GitHub who you are (read:user), never sees your code, and keeps just your id, login and avatar. Then you can:

  • Keep it, on your terms. Commit your own slopscore.md (spec) and press Refresh. Your paperwork replaces the Cap'm's, and you can submit it for Slop of the Day.
  • Take it down. One click on Remove. It stays gone; the trawl never brings it back.

Log in with GitHub

Can't log in as the owner? Request a takedown. No login needed, and a trawled listing comes down right away.

GitHub says
Self-hosted face and object recognition — REST API + browser UI in one container. Enroll people by name, review uncertain matches, detect objects. InsightFace + YOLO, GPU auto-detected, SQLite, no cloud.
website
https://michaelyagi.github.io/argus/
topics
dockerface-recognitionfastapiinsightfaceobject-detectiononnxruntimepythonself-hostedsqliteyolo
created
2026-06-19 · pushed 1 hour ago · 587 commits · 1 contributor
languages
Python 63%HTML 25%JavaScript 9%CSS 2%Shell 0%PowerShell 0%
paperwork
licensereadme 42% health
dependencies
no dependency graph (no manifest, or disabled) · OSV.dev, checked 1 hour ago

Disclosures, inferred by the Cap'm

slopbucket
vibe-coded
category
other
ai_generated
mostly
human_touch
light
status
works-on-my-machine
language (detected)
cssdockerfilehtmljavascriptpowershellpythonshell
topic (detected)
dockerface-recognitionfastapiinsightfaceobject-detectiononnxruntimepythonself-hostedsqliteyolo
license (detected)
mit

The Cap'm's log

The Cap'm wrote this paperwork, not the owner. This repo never submitted itself to SlopScore. The Cap'm picked it by hand: Self-hosted face and object recognition — REST API + browser UI in one container. Enroll people by name, revie; its own README says "100% of the code was written by Claude (Anthropic); I shaped the architecture, scope, and every decision, and did all the testing". It carries the MIT license. The disclosures above are his best guess from what GitHub shows.

Is this yours? Commit a real slopscore.md and press Refresh to replace this, or remove the listing in one click. There's no account to make: you log in with GitHub.

README — the repo's own words, folded up so the grading fits on one screen

Argus

AI-authored. 100% of the code was written by Claude (Anthropic); I shaped the architecture, scope, and every decision, and did all the testing.

Self-hosted face and object recognition — a clean HTTP API for other apps and a full human curation UI in one container. Enroll people by name, match them across photos, review uncertain matches, and keep everything on your LAN.

Documentation →

Features:

  • Face detection and recognition (InsightFace/ArcFace) — enroll people by name, match across photos
  • Object detection via standard YOLO (80 COCO classes) or YOLO-World (open vocabulary — detect anything)
  • Review queue with ranked match suggestions, configurable thresholds, and auto-confirm
  • Suggested people — clusters unlabeled faces into proposed identities; name a cluster to enroll everyone at once
  • Manual face tagging with click-drag bbox drawing and a three-tier embedding fallback
  • Per-user accounts, named API keys, and environments (isolate data into named workspaces)
  • Webhooks, change feed, external_ref correlation ids, and batch endpoints for integration
  • Bulk detection with async mode and job tracking
  • Identity merge, reprocess, export and import
  • Live settings and hot-swap models — no restart needed
  • GPU auto-detected; full CPU fallback
  • REST API — everything the UI does is available via API
  • Mobile-responsive browser UI

Supported image formats: JPEG, PNG, WEBP, BMP, GIF (first frame), TIFF, HEIC/HEIF, AVIF, MPO (first frame)

Quick start

git clone https://github.com/MichaelYagi/argus.git
cd argus
docker compose up --build

Open http://localhost:8100. The first user to sign up is the admin.

Full setup guide, native run, GPU configuration, and API reference: michaelyagi.github.io/argus

License

MIT

Read the rest on GitHub

Scan report · 2026-10-10
  • ✓ Prohibited terms or links
  • ✓ Repository eligibility
  • ✓ slopscore.md paperwork
  • ✓ Content policy
  • ✓ Risk review

0 comments

log in to comment.

report this listing — log in to report