Jev in production › SDKs and workflow integrations

jevcache

Local cache that memoizes Jev decisions keyed on model, schema and redacted state, so repeat calls cost nothing and CI can replay fixtures to catch model drift; runs as a CLI or HTTP sidecar.

Open on GitHub ↗

The source publishes no measured number.
Use
SDKs and workflow integrations
Industry
AI infrastructure
Form
Open-source tool
Stage
In production
Listed
2026-09-20
Found via
github
Repository
hyperspaceai/jevcache
Stars
75
Forks
3
Last push
2026-09-19
License
none stated

The README opens with

The decision ledger for Jev-class models. A Jev decision is (approximately) a pure function of (model, schema, state) — so it's memoizable. jevcache caches those decisions locally: same decisions, fewer bills, and deterministic replay in CI. It's backend-agnostic — point it at any local decision endpoint, a hosted Jev provider, or a mock — and it never proxies or resells inference (your key stays on your machine).

- Local-first & offline. An embedded, zero-dependency store (in-memory map + append-only log). A point lookup is a map access — instant. - Private by construction. State is redacted and canonicalized before it's hashed, so the fingerprint is over decision-relevant content only; PII (emails, phones, long digit runs) and volatile fields...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for sdks and workflow integrations