replayable-evidence
Portable, content-addressed reliability evidence for LLM systems. Capture how a model behaves under perturbation; preserve, verify, and diff the evidence across model changes.
Runtime evidence layer for agentic AI — signed audit chain, deterministic gate verdicts with record-bound audit replay. pip install phionyx-core.
Inspect AI bridge — Phionyx runtime evidence exported into Inspect eval logs. Offline-inspectable evaluation records.
