mtlm-router / catalog / harassment
a lane is a rules.json or .head pack — write your own (RULEPACK.md)
harassment@0.1.0 · 2 routes
Flags directed abuse — you-anchored insults ('you are stupid'), threats ('i will kill you'), dismissal ('shut up') — distinct from profanity's vocabulary focus: harassment is target-directed. ~0ms.
Free demo endpoint, no signup. Same call your agent would make.
clean, harassment
Covers direct second-person abuse formulas — the most common harassment shape in comment spam. Sarcasm, context-dependent abuse, and third-person targeting are model problems; this is the deterministic first pass.
python3 tools/lane_install.py harassment@0.1.0 --apply --appliance . python3 tools/lane_repro.py harassment-0.1.0.lanepack.tar.gz --url http://localhost:8402 # re-run the published eval yourself
sha256: 21d02c85773566d9a1ce0450… · Apache-2.0 · download lanepack
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