Jev (TypeSafe AI)
Transformer that outputs calibrated decision probabilities instead of text; outputs defined in advance so it cannot hallucinate.
Why it matters
A non-LLM decision model: calibrated probabilities out, no text, no hallucination, output tokens free.
What you could build with it
Use as a go/no-go gate anywhere a system needs a calibrated yes or no: deployments, triage, approvals — typed judgments that cannot hallucinate.
Does it hold up?
The strongest implementation ecosystem in the radar. Consistently validates Jev for low-latency gating, routing, triage and repetitive action selection - with one boundary: deterministic code must keep arithmetic, policy, validation and irreversible execution.
Built with Jev
- Meet Jev, the new AI model built to make decisionsindianexpress · Reports Jev was added within days to the stacks of Vercel, Cloudflare, LangChain and Langfuse.
- Jev AI model explained: why developers choose decision-making AImathrubhumi · Notes early users running software automation, classification, model routing and agent monitoring on Jev at sub-half-second decisions.
- browser-use/jev-ultrafastgithub · 19,370 ★ · Dynamic indexed browser-action space where Jev picks operation and target; verified Google Flights task in 7.073s.
- AgentiLoop/Agentgithub · 632 ★ · Full macOS agent using Jev as a second opinion before running shell commands.
- y0usaf/pi-jevgithub · 144 ★ · Pi coding-agent tool-call gate, output judge, leak detection and failure classification; 126ms median judge latency across 203 requests.
- Brainwires/jevwiregithub · 18 ★ · Seven MCP tools, an embeddable decision library and a Claude Code enforcement plugin for Jev.
Learn more
First spotted on article: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.