mtlm-router / catalog / violence

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

Threats & graphic violence

free · certified

violence@0.1.0 · 2 routes

Flags explicit threat and violence phrasing — 'im going to kill you', 'i want to stab someone' — while contextual mentions ('action movie violence') stay clean. Anchored to threat verbs, not the word 'violence'.

Try it live — pinned to expert:"violence"

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

Taxonomy (2 routes)

clean, violent

Honest limits

Covers direct threat formulas and graphic-violence references — the last mod_policy 'unchecked' category with a text lane. Distinct from extremism (ideological) and harassment (abuse): this is raw physical-harm signal.

Install

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

sha256: 27ccfd8c1b2f8433ab28e414… · 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