7
daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill
Research and benchmarks — page 5
Benchmarks, papers and independent reproductions. Read these when you need to understand behaviour rather than adopt a library.
537 active projects in this collection. All collections →
Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence
Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.
Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs
7
A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval
Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.
Discriminative Monte Carlo Tree Search using System One and Harnesses
LegalForecast-MTD benchmark alpha and official evaluation workflows
6
JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default
6
Self-hosted Jev decision workbench and Feishu bot: automatic choices, probabilities, and experimental word/character writing.
Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.
Desktop app for paper-trading stocks and crypto on live prices, with TypeSafe's Jev making the calls and your stops, targets and limits enforced in code. Windows and macOS; never touches real money.
6
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.
6
Make room for useful evidence. Inspectable context selection for RAG, with Jev reranking and open benchmark studies.
6
Typed, calibrated decisions from a local model. No text generated.
A show-and-tell capability study for Jev, TypeSafe's System One decision model.
A verification layer for AI evaluations. Checks the instrument, not just the score: data, scorer, runs, numbers, claims, and itself.
ReflexBench — open benchmark and evaluation harness for System One models and typed decision engines
5
Blazing-Fast Token-Efficient Intrusion Detection System (IDS) based on TypeSafe's Jev.
5
An instrumented 2048 web lab where every move is a Jev (TypeSafe AI System One) Choice, with no heuristic fallback | 用 Jev 决策模型驱动每一步的 2048 网页实验台，概率、置信度、延迟与成本全部摊开可见，且刻意不做启发式兜底
5
React components that resolve which component to render, how to order a list, and whether to show an affordance — from calibrated judgments returned by TypeSafe's Jev.
Community-maintained Go SDK for the TypeSafe AI System One evaluation API, with typed questions, fluent builders, retries, and examples.
5
Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates.
5
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.