Search Packages

glassbox-mech-interp

Mechanistic interpretability + EU AI Act Annex IV compliance. 21/21 frameworks: ACDC edge-circuit discovery, multi-arch GQA/RMSNorm adapter (Llama-3/Mistral/Phi-3), cross-model comparison, causal scrubbing, DAS, Hessian bounds, BH FDR, folded LayerNorm, SAE polysemanticity, multi-corruption, held-out validation. Dual-licensed (MIT core + BSL 1.1 compliance engine).

regaudit-fhe

Depth-tracked regulatory audit primitives for privacy-preserving AI audits with signed envelopes and TenSEAL CKKS support.

insurance-fairness

Proxy discrimination auditing for insurance pricing — FCA EP25/2, Consumer Duty, bias metrics

tanml

Automated validation toolkit for tabular ML models in finance and regulated domains.

glassbox-mcp

Open-source EU AI Act Annex IV compliance toolkit. Mechanistic interpretability + circuit discovery for transformers. One function call generates a court-ready evidence package

xplia

XPLIA - State-of-the-art AI explainability library (2025). Features multimodal explainability, fairwashing detection, uncertainty quantification, and regulatory compliance tools for trustworthy AI systems.