Bài đăng ra mắt Jev
Diogo Almeida giới thiệu Jev, mô hình ra quyết định có cấu trúc của TypeSafe. Xem bộ phim giới thiệu và khám phá chuỗi gốc để tìm hiểu cách tiếp cận, ví dụ và hiệu năng được báo cáo bởi tác giả.
A FIELD GUIDE TO JEV / VOL. 01
Tinh hoa Jev: dự án thực tế, hướng dẫn hữu ích và ý tưởng từ khắp internet.
Diogo Almeida giới thiệu Jev, mô hình ra quyết định có cấu trúc của TypeSafe. Xem bộ phim giới thiệu và khám phá chuỗi gốc để tìm hiểu cách tiếp cận, ví dụ và hiệu năng được báo cáo bởi tác giả.
Thông báo chính thức ra mắt TypeSafe giới thiệu phòng thí nghiệm và hướng người phát triển đến Jev. Bao gồm bộ phim giới thiệu của Diogo Almeida và lời giới thiệu ban đầu.
TypeSafe thông báo truy cập công khai vào Jev mà không cần danh sách chờ. Bảng điều khiển chính thức là điểm bắt đầu để thử nghiệm các quyết định có kiểu trong ứng dụng của bạn.
TypeSafe nhấn mạnh cách tiếp cận đầu ra có kiểu của Jev: các ứng dụng cung cấp trạng thái và câu hỏi, sau đó thực hiện hành động dựa trên xác suất, lựa chọn hoặc điểm số. Thông báo liên quan cũng đề cập đến tích hợp API Venice.
Start with the Launch Post. Explore four official signals.
1.198 tài nguyên
AI-assisted summaries and translations. Check original sources for context and performance claims.
Preview of fast browser use with Jev and OpenCode's browser CLI.
Source-linked curation
A user creates music by giving real-time voice commands to Jev.
Source-linked curation
A test project based on Jev AI, the goal is to build a search function for a blog/article website that has 100s of articles to search from, So the user can actually use the search as chat to question anything and find related answers/articles.
Source-linked curation
Jev (TypeSafe) 性能評価プロジェクト — 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証.
Source-linked curation
A Chrome extension using Jev to filter out AI-generated content from YouTube, caching results for efficiency.
Source-linked curation
Jev model demonstrates fast decision-making in a strategy game. Achieves high-speed gameplay with minimal visual feedback.
Source-linked curation
A community post demonstrating Jev playing Flappy Apex, achieving a high score autonomously through Appduct and Fable.
Source-linked curation
A community post suggesting Jev can be hired as a QA tester through @typesafeai.
Source-linked curation
The Neuron's explainer on AI decisions without a chatbot.
Source-linked curation
Jev vs Jev gomoku with source and timing logs.
Source-linked curation
A community test comparing Jev's performance against GLM 5.3 in a chess game, highlighting speed and cost efficiency.
Source-linked curation
Reduces context usage by 30-55% through Jev-based compaction for OMP agents.
Source-linked curation
Test report using Jev to check each agent action first: most attacks caught, almost no false blocks.
Source-linked curation
Ruby client for typesafe.ai.
Source-linked curation
Desktop writing app using Jev for fast structured writing judgments.
Source-linked curation
One sentence becomes six room settings. Jev chooses, the app renders.
Source-linked curation
Jev analyzes session replays to identify issues and generate bug fix PRs at low cost.
Source-linked curation
Jev classifies 500 emails quickly and inexpensively, demonstrating its efficiency in processing tasks.
Source-linked curation
GitHub Action for issue triage that abstains: label, spam, needs-info and duplicate in one call, each applied only above a threshold you set, and nothing at all below it.
Source-linked curation
Jev automates the filling of prompt boxes by selecting appropriate agents, models, or computers for specific tasks.
Source-linked curation
Pull request adding Jev to station-suggestion reranking in the TrainLCD transit app.
Source-linked curation
Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.
Source-linked curation
Jev processes game state data to make decisions and play Super Mario Bros. effectively.
Source-linked curation
Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive.
Source-linked curation
The first general-purpose System One agent for Jev.
Source-linked curation
Idiomatic Java SDK for TypeSafe AI Jev System One decision engine.
Source-linked curation
Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。
Source-linked curation
JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.
Source-linked curation
Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.
Source-linked curation
A developer project related to market analysis using Jev, collected for the markets shelf.
Source-linked curation
A tool that provides quick actions based on clipboard content, specifically for macOS.
Source-linked curation
A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.
Source-linked curation
A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.
Source-linked curation
A research project on GitHub uses Jev with Qwen3 models on an NVIDIA DGX Spark system.
Source-linked curation
Probably: live BTC, ETH, and XRP prices with a shared TypeSafe buy-or-wait demonstration. No trades placed.
Source-linked curation
A plugin using Jev's scoring capability to remove unnecessary terminal garbage and redundant logs, improving agent performance.
Source-linked curation
TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.
Source-linked curation
Antivirus scanner and real-time defense sentinel: extracts structural features from executables, scripts, and documents (entropy, hashes, strings, PE imports) and has Jev judge whether each is malicious.
Source-linked curation
A demonstration of Jev competing against OpenJev in a first-person shooter game.
Source-linked curation
Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill.
Source-linked curation
Turn any open model into a classifier/jev endpoint.
Source-linked curation
Fork of OpenPoke where the yes/no decisions go to Jev instead of Claude Sonnet, with a same-inputs A/B against the replaced LLM decision and a 43,776-request adversarial run on the injection gate.
Source-linked curation
JevNoiseGate filters unwanted notifications and SMS on Android. Rather than matching keywords, an LLM decides what's noise — and only what it explicitly flags is blocked. Verification codes are matched on-device and never uploaded; anything uncertain passes through.
Source-linked curation
Context curator for Pi agent using Jev technology.
JEVLAB ARTSource-linked curation
A chat bot using Jev without a large language model, providing instant responses by integrating web search, Wikipedia, weather, and other tools.
Source-linked curation
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs.
Source-linked curation
Unofficial typed async Rust client for the TypeSafe System One API.
Source-linked curation
Curated catalog of System One / Decision Models — contributions for modelsystem.one.
Source-linked curation
A tool that uses Jev to detect AI-generated content on websites by analyzing specific indicators.
Source-linked curation
Rule-based slop grader for text files powered by Jev: evaluates markdown against customizable rulesets, outputting violation flags and scores for an AI agent to auto-fix.
Source-linked curation
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.
Source-linked curation
Browser extension that classifies an article's framing, type, topic, and loaded language with Jev.
Source-linked curation
A sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world.
Source-linked curation
One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.
Source-linked curation
Kỹ năng đại diện chính thức cho Claude Code, Codex và các đại diện tương thích: các nguyên mẫu, mẫu và cách cấu trúc đánh giá.
JEVLAB ARTSource-linked curation
An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games.
Source-linked curation
Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on.
Source-linked curation
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Source-linked curation
A developer project that selects applicable rules for Claude, ensuring only relevant information is shown.
JEVLAB ARTSource-linked curation
Agent makes rapid shopping decisions using Ego Lite and Jev. Completes 20 product evaluations in under 4 seconds.
Source-linked curation
A free open-source search tool powered by Jev and a search API for plain language queries.
Source-linked curation
An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick.
Source-linked curation
Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.
Source-linked curation
TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer.
Source-linked curation
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.
JEVLAB ARTSource-linked curation
A GitHub project enabling voice-controlled Mac automation without vision models.
Source-linked curation
A developer project that converts vague agent requests into deterministic commands for improved reliability.
Source-linked curation
LegalForecast-MTD benchmark alpha and official evaluation workflows.
Source-linked curation
Official TypeSafe reference: Confidence-gated routing.
Source-linked curation
Playjev uses Jev for browser automation with decision-making capabilities.
Source-linked curation
A tool for automated risk review of pull requests using Jev.
Source-linked curation
Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.
Source-linked curation