untell — tool profile and history

AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude Code skill + Python CLI. MIT.

Active

Canonical source ↗

Language
Python
License
MIT
Created
Last activity
Topics
  • ai-detection
  • ai-detector
  • benchmark
  • claude-code
  • claude-code-skill
  • detector-evaluation
  • false-positives
  • gptzero
  • model-evaluation
  • nlp
  • open-source
  • python
  • reproducible-research
  • robustness-testing
  • turnitin
  • unicode-security
  • writing-tools
  • zerogpt

Current measurement

19GitHub stars+2 (+11.8 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
19GitHub stars
18GitHub stars
18GitHub stars
18GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
16GitHub stars
16GitHub stars
16GitHub stars
14GitHub stars
13GitHub stars
12GitHub stars
12GitHub stars
12GitHub stars
10GitHub stars
9GitHub stars

Classifications

Domains
Type
Other
Use cases