Jev Cursor

System One routing for coding agents where Jev decides and the LLM generates: an OpenCode v2 plugin, Cursor hooks and a skill cover turn steering, tool-call redirects, permission gating, failure advice, subagent routing, code review and on-demand jev_ask decisions.

Four advisory decision tools for AI agents, shipped as a zero-dependency stdio MCP server backed by the TypeSafe System One API (Jev model). Each tool builds exactly one Choice question and returns a decision; nothing is ever executed.

Jev-scored context recovery for the Cursor CLI agent: hooks capture tool call and result I/O, two noul questions per call decide what to keep, and kept facts are re-injected verbatim after native compaction finishes.

A local MCP server that runs ready-made Jev question packs for Cursor and other agents: typed Choice, Noul and Score judgments over closed state, with run_questions as the custom path when no pack fits.