jev-alternative

JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint

Open-source, local Jev alternative: a System One decision layer with provably calibrated confidence (ECE 0.170→0.071). Typed decisions, runs offline, no API key, no waitlist.

⚡ Foq — the FREE, local, open-source alternative to Jev. Typed System 1 decisions in ~25 ms — no waitlist, no cloud, no per-token cost. foq.fr

Run fast, typed AI decision models behind one API. Choice, score and yes/no decisions with multiple engines and hardware backends.

when a gopher met Jev

Windows port of Laya typed-decision AI (ONNX Runtime + DirectML) — Core ML/Apple Neural Engine alternative with first-class Arabic support. No text generation, no hallucination, runs on any DX12 GPU.

Native Laya-MLX integration for squad agents in Codex, Claude Code, DeepSeek Harness, and Pi—installed with one command.

Laya 0.4B: The Free Jev Killer That Answers in 32ms! Sub-35ms open-weight System 1 decision model running real-time Pong AI.

通用客服平台:ChatKit UI + Jev 决策 + Qwen 生成 + RAG 知识库 + 插件化 Tools + MCP 数据面,换行业只改 YAML 不改代码

Dockerized REST service, jev-compatible, that serves the Laya model (convaiinnovations/laya) for use from non-Python apps.

Jev-like Fast Decision Machine (JLDM) with image support

Job search in Denmark: aggregates vacancies from jobnet.dk and jobindex.dk, filters them against a profile, ranks matches with the Laya decision model, and outputs terminal tables plus a Markdown report.

Jev AI agent skill for typed decisions

Clanker frustration insights, powered by on-device Laya decision model.

Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.

Jev-trading is a desktop application that combines the ultra-fast neural network model Jev (by TypeSafe AI) with an intuitive visual interface. We've created a platform where the power of algorithmic trading is accessible without writing a single line of code, messing with Python scripts, or configuring servers in the terminal.