4 projects
nakata-truthcheck
Open-world fact verification for AI claims (sibling to halluguard, which handles closed-world).
halluguard
Reverse-RAG hallucination detector. No LLM judge. Vendor-neutral.
adaptmem
One-shot domain adaptation for retrieval — beat your baseline with 200 lines of hard-negative mining.
claimcheck
Domain-tuned retrieval + zero-LLM claim verification in one pipeline.
