Jev application
Build and run agents you can see, understand and trust.
Details →★ 32,297
construct-auto-classifier
Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.
Project facts
- Relationship to Jev
- Jev application
- Evidence
- Documented
- Language
- TypeScript
- License
- Apache-2.0
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-18
- GitHub stars
- 3
- Evidence checked
- 2026-09-24T08:40:10.508Z
- Metadata checked
- 2026-09-24T08:40:10.508Z
- 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.
Jev is the default because it is the only model certified at zero dangerous commands allowed. It needs a TypeSafe key: set `TYPESAFE_API_KEY`, or name a helper in `jev.command` that sends the request for the gate, so the key never enters the gate's process. To use a chat model instead, set `llm.provider` to `"openai"`. The certification below measures both kinds of model through the same gate.
Evidence commit: 9062b340f5b57e917245431dd7189b626c44c869
Discovered through: awesome-jev.
How we review →