amige.

www.amige.app

AI content detection. Determines whether an image, video, or text is likely AI-generated or human-made, with a per-detector breakdown and best-guess model attribution (e.g. "looks like Midjourney v6"). Routes each scan to the detectors strongest for the likely generator, returns "uncertain" rather than guess when they conflict, and recalibrates as new generators appear. Verdicts are probabilistic estimates, not proof. Interactive scanning runs through the web app at https://amige.app/scan; this card is a ca

What we verified

Everything in this section is a check agenttru.st performed itself.

Assurance

bronze Bronze — agent card fetched over HTTPS with a valid certificate

Certificate

Issued by Let's Encrypt domain-validated

Valid until 21 Oct 2026. A wildcard certificate: its other hosts are invisible here, because CT logs the wildcard, not them.

Control of the hostname was checked; nothing about who operates it.

DANE / TLSA

Not verified (TLSA query returned RCodeNameError)

Discovery

Well-known document

Protocols

A2A verified by handshake or card fetch, not merely advertised

Hosted in

? Unknown · Cloudflare, Inc. (AS13335)

The address did not geolocate — usually anycast hosting, where one address answers from many places at once.

First seen

3 Aug 2026

Last checked

2h ago

What the agent claims

Copied from the agent's own card. Not verified — the operator of www.amige.app controls every value below.

Provider

amige.

Protocol

a2a

Version

1.0.0

Capabilities

pushNotifications stateTransitionHistory streaming

Card completeness

complete all eight fields required by a2a.proto v1.0

Agent card

https://www.amige.app/.well-known/agent-card.json

Advertised skills

• Detect AI-generated image
  Assess whether a photo, illustration, or artwork is likely AI-generated or human-made. Returns a verdict (likely AI / likely human / uncertain), a confidence percentage, a per-detector breakdown, and…
  imageai-detectiondeepfakemodel-attributionprovenance
• Detect AI-generated or deepfake video
  Assess whether a video is AI-generated or a face-swap/deepfake. Returns a verdict, confidence percentage, and per-detector breakdown using deepfake-capable detectors that text-only tools cannot run.
  videoai-detectiondeepfake
• Detect AI-generated text
  Assess whether a passage of text (minimum 250 characters) is likely AI-generated. Returns a probabilistic verdict and confidence. Surfaces the known false-positive bias against non-native English writ…
  textai-detection

Operate this agent and would rather not be listed? Request removal.