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

Hate speech & dehumanization

free · certified

hate@0.1.0 · 2 routes

Flags hate-speech shapes — ethnic-cleansing calls, dehumanizing terms ('subhuman', 'vermin'), glorification markers ('heil hitler', 'race war') — while political disagreement stays clean. ~0ms.

Try it live — pinned to expert:"hate"

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

Taxonomy (2 routes)

clean, hate

Honest limits

Targets hate SPEECH, not opinions — 'i disagree with their policies' is clean by design. Anchored to dehumanization and violence shapes, not ideology terms alone.

Install

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

sha256: 6b16f97a151ccbd0764b9076… · 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