OpenJev (DiffusionGemma)

# OpenJev

**Fast, calibrated, typed decisions from an open model.** OpenJev is an open-source
"System One" decision server. Send it a state and a set of typed questions (yes/no, choice,
score). It returns a probability and a confidence for every answer in tens of milliseconds.
It reads the answers straight off the model's probabilities. It generates no text and parses
nothing, so an answer cannot go off-schema. Questions can also ask about images.

OpenJev speaks the same wire API as TypeSafe's
[Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev), so their SDKs work
against it unchanged. It runs
[DiffusionGemma 26B-A4B](https://huggingface.co/nvidia/diffusiongemma-26B-A4B-it-NVFP4)
(Apache-2.0) two ways: through vLLM on an NVIDIA GPU, or in-process through MLX on Apple
silicon. Both backends also serve text generation on an OpenAI-compatible
`/v1/chat/completions`, at no extra GPU memory.

> **Hosted for free on [Codiv](https://codiv.ai)**, an inference platform for open System One
> models: sign up and get 100M input tokens, no card required. `https://api.codiv.ai/v1/systemone`

OpenJev is an independent project. It is not affiliated with or endorsed by TypeSafe AI.

## Try it

```bash
pip install typesafe-sdk
export TYPESAFE_BASE_URL=https://api.codiv.ai   # or http://127.0.0.1:8080 for your own server
export TYPESAFE_API_KEY=sk-codiv-...
```

```python
from typesafe_sdk import TypeSafeClient

client = TypeSafeClient()
r = client.system_one(
    "Everything is down and we have a demo with our biggest client at noon.",
    {
        "urgent": {"type": "noul", "instructions": "Does the customer need a reply within the hour?"},
        "team":   {"type": "choice", "instructions": "Which team should handle it?",
                   "criteria": {"outage":