Jev, for your day‑to‑day work.

Install, set your key, done

curl -fsSL https://jevx.deemwar.com/install.sh | sh
export TYPESAFE_API_KEY=...

Your agent, or you

$ jevx filter "Is this line an error an on-call engineer would act on?" < app.log
2026-09-27 10:03:40 ERROR payment gateway timeout after 30s (order 4021)
2026-09-27 10:04:02 FATAL db connection refused: too many clients

$ jevx is "Does this command overwrite history on a shared remote branch?" --in "git push --force origin main"
yes 0.96

Your agents already know it

One install teaches Claude Code and Codex when to ask Jev, and what to do with yes, no or unsure.

Your instructions are the context

It reads the ## Jev section of the AGENTS.md / CLAUDE.md you already keep. Nothing new to maintain.

Judge against your own notes

--memory sends the best-matching sections of your docs after the item: a 0.4B local model went from AUC 0.30 to 0.86 on 68 held-out claims. --memory-strict catches changed numbers (40 of 40).

Repeat calls are free

Answers are kept on your machine, keyed by a hash, so asking the same thing again returns in milliseconds and costs nothing. On by default; --fresh asks again.

Guards at agent events

Stop an rm -rf, flag an injected web page, check a turn before it is handed back. Off until you turn it on.

Getting startedTwo minutes.

Agent scenarios18 real situations and the answers Jev gave.

Compared with other Jev toolsAnd when to use them instead.