jev-alternative

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

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

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

A Bangla-focused adaptation of Laya for typed decisions, classification, and routing.

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

A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.

A decision model that returns calibrated answers to yes/no, choice, score and multi-label questions.

⚡ 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

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.

when a gopher met Jev

The Awesome List of Awesome Jev Lists

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

Jev AI agent skill for typed decisions

A list of System One models (also called decision models): Jev, the first, plus open and hosted alternatives, agents, tools, SDKs and benchmarks.

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

Open-source playground for evaluating System One and JEV-compatible models with deterministic fidelity, semantic judging, and independent verification.

User → Jev(Laya) → Agent — a local System-1 decision layer for DeepSeek Harness agents. Laya (open, Jev-compatible) routes prompts, gates risky tool calls and swaps models in milliseconds. 100% local, $0/token. MIT.