Pointing an existing Jev client at another model or host without rewriting the question or answer types.
Ollaya, Lichen, verdict, and Rizzo Flow are used by changing the base URL. System One Connector does the same for agents and can set TYPESAFE_MODEL when the local server is CLM. The request body — state, model name, and the question map — stays in the System One shape.
A swap still changes answers. Option limits, Noul-only servers, uncalibrated confidence, and a server that ignores API keys are all compatible at the JSON layer and different in behavior. Log the model field that comes back, not the alias you sent.
Definitions that connect to this one.
ollaya-dev/ollayaRust
Mushroom-Systems/lichenPython
khimaros/verdictPython
Rizzo-AI-Academy/rizzo-flowPython
itsmostafa/system-one-connectorGoPosts from builders shipping with Jev right now.
A Krunker-inspired FPS, decided by Jev
Maybe I’m just washed, but Jev is beating me at my own game. Built a Krunker-inspired FPS where you 1v1 Jev. Try it out yourself: jev-arcade.vercel.app/duel
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Pixel art out of 256 multiple-choice questions
I turned @typesafeai Jev model into a pixel art model. 256 multiple choice questions, one per pixel, plus refinement passes. These were the best results out of the bunch I tested. Code: github.com/Wizhill05/type…
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
An Elixir port of the official SDK
[Announcing] TypeSafe SDK - Jev, the first System One model from TypeSafe forum.elixirforum.com/t/76700 #ElixirLang #MyElixirStatus
jod: Zod validates data, Jev judges it
Zod validates data you already understand. Jev judges data you don't. jod is the seam: your state validates locally and for free, every question goes out in one parallel request, and typed answers come back. github.com/mateonunez/jod
Loki: a self-improving harness with a Jev companion
You can run Jev at home with Loki as well! It’s a full agent harness github.com/wundercorp/loki
Jev as an LLM guardrail inside Agentgateway
TypeSafe’s new Jev model is fast 🔥 and Agentgateway keeps up! In minutes, I had Jev running as a prompt guard through Agentgateway, with distributed tracing and cost tracking. Check out the example below Example: github.com/agentgateway/a… Intro to Jev: typesafe.ai/blog/introduci…
