Jev Policy

A Pi extension that checks proposed code edits against your repository's Markdown rules with TypeSafe Jev and returns the exact instruction text and source line range for each violation. Informative mode reports; enforcement mode blocks reviewed code.

A judgment layer for agents that starts with Claude Code: a PreToolUse hook asks a YAML policy you own a handful of plain-English questions about every proposed tool call, and Jev returns calibrated probabilities so thresholds — not a frontier LLM — decide allow, deny or silence, for about four cents a day.

An open-source Jev-based MCP router: it discovers, catalogs, classifies and deduplicates every MCP server and tool you have, then exposes each agent only the small, authorized subset it needs for the task. Routing decisions are System One Choice/Score/Noul questions, scored by a pluggable engine at the edge or hosted.

A provider-agnostic decision gateway that puts Jev in front of expensive generative LLMs: small bounded questions are batched through Jev, a deterministic policy layer builds the execution plan, and generation runs only when the policy says so.

KITE queries a typed behavioral kernel once per unique state, then runs populations of any size from the table, reserving an expensive flagship model for sparse paired anchors. On Epstein experiments with 9,070 participants, anchors covering 1.7% of states cut effect error by 41%.

Python library that records each Jev-class decision as the full distribution under a sha256 key of state, question, provider and model, then applies a separate policy. Thresholds, review bands, routing and budgets can change across the recorded history without new model calls.