Pinned Loading

1. agent-debate agent-debate Public

   Multi-agent advocate/skeptic/judge debate for any consequential decision. Hiring, product, policy, architecture, M&A. Surfaces uncalled risks.

   Python

2. bio-bench bio-bench Public

   Narrow eval harness for LLMs on biological reasoning. Five task families, 80 examples, deterministic scoring.

   Python

3. clinvar-classify clinvar-classify Public

   Research probe: LLM-assisted clinical variant classification with retrieval bundles. 60 ClinVar variants, no training.

   Python

4. life-scenarios life-scenarios Public

   Scenario engine for major life-event decisions. Career breaks, relocations, education funding, large transactions. Numbers, risks, and recommended actions.

   Python

5. prompt-eval-arena prompt-eval-arena Public

   Rigorous A/B harness for prompt iteration. Both deterministic and LLM-as-judge scoring. Paired Wilcoxon, effect sizes, replicate-run variance.

   Python

6. stablecoin-policy stablecoin-policy Public

   Selective-disclosure policy engine for stablecoin payments. Per-role views, predicate attestations, declarative policy language. TypeScript.

   TypeScript