JevLang
By TimMikeladze
Source description: A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.
Repository description
The repository describes its purpose as: A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.
Source evidence
The daily check found an explicit Jev / TypeSafe AI connection in the original README and implementation files at the same commit.
```sh $ node ask.js # live: one real ticket sent to the hosted model page retention-oncall // angry refund request route 0, $.route.clauses[0] because refund-requested? = 0.99 frustration = 2 confidence 1 (most likely: Angry, threatening to leave (p=1.00)) answered by typesafe jev-1.13.0 ```
Automatically source-checked: public repository, pinned README, and implementation files. Not run, benchmarked or security-audited.