jev-axi
Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell
How it uses Jev
A second opinion for coding agents, in half a second. jev-axi is a CLI for TypeSafe's Jev, a model that never writes text — it answers typed questions with calibrated probabilities, in about 400ms for a few thousandths of a cent. That makes it cheap enough to put in front of every command your agent runs.
Getting started
The TypeSafe API reports per-request token counts but has no spend endpoint, so jev-axi keeps a ledger of every call in your config folder ( /.config/jev-axi/stats/usage.jsonl ). Each record has the command, model, tokens, latency, cache status, the project it ran in, and how many answers landed in each confidence ban…
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.