Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
jevshield
Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- Apache-2.0
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-20
- GitHub stars
- 2
- Evidence checked
- 2026-09-24T11:38:35.000Z
- Metadata checked
- 2026-09-24T11:38:35.000Z
- Check status
- current
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
# export TYPESAFE_API_KEY="ts-..."
Evidence commit: 2bbd20db51aee84e77da513935ce7fc364bb9d06
Discovered through: awesome-jev.
How we review →