a lane is a rules.json or .head pack — write your own (RULEPACK.md)

Profanity / obscene-term detection

free · certified

profanity@0.1.0 · 2 routes

Wordlist lane over 403 terms (LDNOOBW public list): 'clean' vs 'profane' in ~0ms with zero model cost. The deobfuscation layer catches obfuscation for free — 'f u c k', 'sh1t', 'FvCk', 'a$$hole' all resolve to the listed term before matching.

Try it live — pinned to expert:"profanity"

Free demo endpoint, no signup. Same call your agent would make.

Taxonomy (2 routes)

clean, profane

Honest limits

Single-token wordlist matching — obfuscation-normalized, but morphological variants that aren't in the list ('fucking', 'phuck') can miss. Multiword list entries can't fire yet. Wordlist = transparent coverage: you can see and extend every term it checks.

Install

python3 tools/lane_install.py profanity@0.1.0 --apply --appliance .
python3 tools/lane_repro.py profanity-0.1.0.lanepack.tar.gz --url http://localhost:8402   # re-run the published eval yourself

sha256: 3d68dd51810cc19a6c6e87c6… · Apache-2.0 · download lanepack

NEED YOUR OWN ROUTES?

A private lane on your taxonomy — trained, calibrated, exclusive. €149 / domain, 3 business days.

Get a lane like this pricing →

generated by tools/render_lanes.py · source: index.json