A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
shizurak
đ° The agent-native blog engine â DSH-Cordis microkernel ¡ 3 GenUI engines ¡ dual-personality theme contract (void à lumen) ¡ Next 16 / React 19 / AI SDK v7. SpaceX space-opera à Apple-minimal.
Project facts
- Relationship to Jev
- SDK / client
- Evidence
- Documented
- Language
- TypeScript
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-19
- GitHub stars
- 0
- 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.
| ⥠| **System One safety gate (Jev)** â [TypeSafe's] non-generative decision model (`@typesafe-ai/sdk`) runs *in front of* the LLM: calibrated-probability prompt-injection screening at the chat edge (403 without burning tokens), dynamic `toolApproval` risk on L2 tools, draft grounding checks. 70â500 ms, hallucination-free typed outputs; degrades open when unconfigured. |
Evidence commit: c708dda0a248f3b76d98451e587259c7e7f53aae
Discovered through: github-search.
How we review â