haluguard/haluguard

Verify LLM output for hallucinations using haluguard.com

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
tokenhaluguard API token (get one at haluguard.com)yes
textText content to verify (alternative to file).no
filePath to a file whose contents will be verified.no
thresholdHallucination score 0..1; if score >= threshold, the action fails. Default 0.7. Pass "0" to fail on any hallucination.no0.7
fail-on-hallucinationsIf "true", any "hallucinations_found" verdict fails the build (overrides threshold). Default "false".nofalse
api-urlOverride the API base URL (for self-hosted / dev).nohttps://api.haluguard.com
namedescription
verdict"clean" or "hallucinations_found"
severityseverity tier: clear / suspicious / unclear / clean
scoreoverall score 0..1
n_claimstotal claims found in the text
n_hallucinationsclaims flagged as hallucinations
reportfull JSON report from haluguard