Build and run agents you can see, understand and trust.
jev-codex-workbench
Codex plugin and MCP server for TypeSafe Jev decisions and recoverable context reduction, with optional local Laya-MLX and token/time measurement tools.
Project facts
- Relationship to Jev
- Integration
- Evidence
- Documented
- Language
- Python
- License
- NOASSERTION
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-20
- GitHub stars
- 1
- Evidence checked
- 2026-09-27T14:12:42.000Z
- Metadata checked
- 2026-09-27T14:12:42.000Z
- 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.
**An open-source Codex plugin and MCP server for bounded AI coding agent decisions and recoverable context.** The workbench adds TypeSafe Jev around the coding model you already use in Codex. Jev handles narrow semantic judgments; Codex remains responsible for code, tools, and execution. Version **1.1.3** adds standing workspace enrollment, compact receipts, extractive tool-output reduction, shared budgets, and an optional local Laya-MLX route.
Evidence commit: cb75adc1eb7d8e38b7eea473ba793223d0cb0bde
Discovered through: github-search.
How we review →