Launches on September 17, 2026

看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.

A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.

A claude code plugin for jev

A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively)

Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.

Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper

Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code

Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)

TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.

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

Interactive TypeScript coding CLI powered by Jev typed decisions and constrained AST generation.

Fast browser agent for ego lite. One TypeSafe request per step; an agent or Jev picks the move.

AI Music (MIDI) generator powered by Jev

Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.

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

Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway

Small dependency-free CLI for TypeSafe Jev

Grill-me with Jev optional each turn

Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM

Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.

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

Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.

Interactive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs.

Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.

This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

TypeSafe Jev as the pi coding agent's quiet decision layer

Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.

One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.

Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.

Backtest Jev (TypeSafe) as a BUY/SELL/HOLD trader on NQ L10 order-book data

Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.

Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows

AskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude)

Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision

Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

Aside agents decide with TypeSafe Jev (System One: Choice/Score/Noul). Not a Cua binding — Jev is the model, Aside is the browser runtime.

DiffJury — TypeSafe Jev PR risk router + code review coach

Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.

Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.

Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels

Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

Grade page sections for clarity, writing and on-page SEO. WXT + TypeSafe AI Jev.

Instinct: describe a case in free text and Jev picks the UI from a fixed catalog without generating a line of code or copy.

High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking

daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill