githubnext/localjev

A local, Jev-compatible POST /v1/systemone API written in TypeScript for Bun, backed by DiffusionGemma through an OpenAI-compatible Chat Completions endpoint. The defaults target: Jev uses a typed decision API rather than an OpenAI chat API. OpenJev implements the Jev wire protocol and obtains probabilities with a special one-step DiffusionGemma structured read. Its backend depends on unmerged vLLM request extensions such as diffusionseedcanvas, diffusionreadonly, and requested token logprobs. The normal oMLX API does not expose those primitives. LocalJev therefore takes the portable approach: entropy-based confidence; This is wire-compatible, but not mathematically equivalent to OpenJev's logit read. The probabilities are generated/self-reported by the model rather than read directly from its logits. Evaluate their calibration on your own workload before relying on them for consequential decisions. Requires Bun 1.2+ and a running oMLX server. Bun loads .env automatically. Alternatively, set the key in your shell before starting the server: LocalJev listens on http://127.0.0.1:8080.…