mtlm-router / catalog / self_harm

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

Self-harm & distress signals

free · certified

self_harm@0.1.0 · 2 routes

Flags explicit self-harm / suicidal-ideation phrasing as 'self_harm' vs 'clean' at ~0ms. Context-anchored patterns — 'suicide squad' and colloquial use stay clean while 'i want to die' and 'thinking about suicide methods' flag.

Try it live — pinned to expert:"self_harm"

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

Taxonomy (2 routes)

clean, self_harm

Honest limits

A triage signal, never an autonomous verdict on someone's welfare — every hit should escalate for human review. Coverage is explicit anchored phrasing; implicit or veiled distress is a different problem. Carefully tuned against colloquial false positives.

Install

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

sha256: 6592193ede19d1b737909769… · 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