Benchmarks & Research for Jev — page 3

Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.

Agentic GraphRAG engine using swappable System One decision models (local Laya / cloud Jev). Features a complete 4-phase pipeline (Ingestion, Pre-Retrieval, Traversal, Post-Retrieval) and evaluation across Neo4j, Memgraph, Apache AGE, and Kùzu driven by a custom A* traversal algorithm.

an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch

sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model

A Minesweeper benchmark for LLM agents. One identical board, up to nine models in parallel, one clock, one tool layer.

Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

Measures what your Jev classifier's confidence is really worth, and sets the human hand-off line from what a mistake costs.

Open-source, local decision models inspired by TypeSafe’s Jev and System One - built on Qwen3 for NVIDIA DGX Spark.

if you're experimenting with jev it will be easier from here

Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.

An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.

openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

ProphetLab's Texas Hold'em benchmark and playground for decision models: cash and SNG leaderboards, live replays, and bring-your-own-agent tables.

Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.

Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers

A Swift package for typed decisions from language models (probabilities, choices, and scores), with support for local MLX models and the TypeSafe Jev API.

Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.

SLO-aware LLM inference router with Jev decisions, live queue metrics, counterfactual evaluation, and reproducible latency/cost benchmarks

Agent skill for finding, building, evaluating, and improving decision-model systems. Compositional decision calculus, eval harnesses, and bounded prompt/program hill climbing for Software 3.0. TypeSafe Jev is the default hosted exemplar. Independent of TypeSafe.

Hermes Agent plans, Jev (TypeSafe) picks bounded actions, Mineflayer executes: Minecraft with no screenshots or keypresses from a model. Includes the reproduction of rmalde/minecraft-agent's Ender Dragon run.

A local, offline System One server compatible with TypeSafe's Jev API. It answers typed yes/no, category and score questions with small open models.

离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev