Build and run agents you can see, understand and trust.
skillbox
Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.
Project facts
- Relationship to Jev
- Integration
- Evidence
- Documented
- Language
- TypeScript
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-17
- GitHub stars
- 234
- 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.
TypeSafe uses `POST https://api.typesafe.ai/v1/systemone`, Bearer authentication and `model: "jev-latest"`, without Gateway protocol headers. Gateway keeps its evaluation-model endpoint and existing headers. OpenRouter uses `POST https://openrouter.ai/api/alpha/decisions` with `model: "typesafe/jev-1.13"`, not the chat-completions endpoint. All three use the same bounded catalog and score rubric. OpenRouter evaluates the complete catalog in batches of at most 32 skills / 24,000 request bytes, wi
Evidence commit: cda64ad3310abe690c6d497352791da4cfeb9a0a
Discovered through: typesafe-field-guide.
How we review →