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.
Phionyx Core SDK - AI↔AI Mediator and Echo Engine
Phionyx MCP trust boundary governance layer — descriptor signing, runtime guardrail, tamper-evident audit chain for MCP-capable hosts.
Interoperability bridge — export Phionyx Reasoned Governance Envelope (RGE) evidence into Inspect AI evaluation logs.
