Ai Auditing Python Packages

ai-code-quality-auditor

An empirical safety harness for agentic AI coding systems: measures whether an AI agent built what the specification asked for, not just whether the code runs. Pre-registered, blinded, open data.

agent-casuality

Causal Debugging for Branching Multi-Agent Systems

inflion

Observability and influence tracing infrastructure for multi-agent AI systems.

regaudit-fhe

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

traceiq

Observability and influence tracing infrastructure for multi-agent AI systems.

standard-block-auditor

Exposing administrative "Vanity Metrics". A framework to audit the true ROI and reach of government policies by decomposing big numbers into municipal-level units. ↓demo

triadic-engine

Deterministic neurosymbolic engine — projects embeddings into prime integers for explainable subsumption, composition, and gap analysis. 30.9x faster than cosine similarity.