Inspect Ai Python Packages

falsify-inspect

PRML pre-registration adapter for Inspect AI eval logs. MIT.

agentsec-bench

Security benchmark for LLM agents & their harnesses — offensive, defensive, secure-coding & prompt-injection-safety challenges on live sandboxed targets, with gradated scoring. Built on Inspect AI.

ai-crucible

A diagnostic adversarial game for frontier LLMs — a measurement instrument that happens to be fun.

petri-braintrust

Export Inspect Petri alignment audits to Braintrust experiments, with first-class Ollama support.

wikigame-agent

Wiki Game LLM agent built on AISI Inspect.

judgecal

Statistically rigorous, batch-first reliability auditing for LLM judges & reward models — clustered-bootstrap CIs, McNemar, BH-FDR, power/MDE, planted-bias validation. No API key required.

phionyx-eval-inspect

Interoperability bridge — export Phionyx Reasoned Governance Envelope (RGE) evidence into Inspect AI evaluation logs.