JEVThe best of Jev. Real projects, practical guides and ideas from across the internet.
Updated 1 Resource
THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POSTDiogo Almeida introduces Jev, a structured decision model from TypeSafe. This resource provides an overview of the model's core approach, practical examples, and performance metrics as reported by the author.
TypeSafe AI@typesafeaiOFFICIALTypeSafe officially launches its research lab and introduces Jev to the developer community. This announcement features a launch film by Diogo Almeida and provides foundational context for the project's mission and future direction.
TypeSafe AI@typesafeaiOFFICIALTypeSafe has removed the waitlist for Jev, allowing public access to the platform. Developers can use the official console to integrate and test typed decision-making capabilities within their own software applications.
JEVLAB ARTTypeSafe AI@typesafeaiOFFICIALTypeSafe highlights Jev’s typed-output approach, where applications provide state and questions to receive structured probabilities, choices, or scores. The announcement also details the integration of the Venice API for developers.
JEVLAB ARTAI-assisted summaries and translations. Check original sources for context and performance claims.
ego-jev integrates the Jev System One model into the ego-lite browser to automate tasks within a single process. It demonstrates a 2x speed improvement over per-step LLM loops by using indexed element tables for decision-making.
JEVLAB ART
简体中文An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
JEVLAB ART
EnglishThis project explores the feasibility of running Jev-based workflows using local large language models. It provides a framework for users to experiment with private, offline implementations of Jev architectures on their own hardware.
JEVLAB ARTEnglishLocal bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.
JEVLAB ARTEnglishThis SQLite extension enables direct integration with TypeSafe Jev, allowing users to execute decision-based AI tasks like classification, scoring, and yes/no probability checks directly within SQL queries using standard libcurl-based function calls.
JEVLAB ARTThis repository provides eight minimal examples demonstrating the application of TypeSafe's Jev model to mechanical and electrical engineering tasks. It illustrates practical use cases including CAD routing, FEM result triage, and BOM alignment without external dependencies.
JEVLAB ARTEnglishThis guide demonstrates how to integrate the Vercel AI SDK for evaluation purposes. The author explores practical implementation steps for developers looking to assess AI model performance within their existing application workflows.
JEVLAB ARTEnglishJevLint provides configurable semantic linting for codebases using Jev. The tool demonstrates file-level NOUL judgments and includes a plugin designed to manage magic strings, offering a structured approach to maintaining code quality through semantic analysis.
JEVLAB ARTEnglishThis Rust library provides a lightweight integration for interacting with the Jev ecosystem by TypeSafe AI. It demonstrates how developers can implement client-side connectivity to Jev services within Rust-based applications.
JEVLAB ARTEnglishThis project demonstrates a Next.js brick breaker game where the paddle movement is controlled in real time by the TypeSafe AI Jev model. The creator reports that the application was developed using Claude Code.
JEVLAB ARTEnglishThis desktop application integrates Jev to provide real-time, structured writing judgments. It demonstrates how the Jev framework can be applied to create Grammarly-style feedback tools for improved text composition and editing workflows.
EnglishThis tool enables automated auditing of git diffs against defined YAML coding standards. It utilizes the Jev model to provide consistency checks directly through a command-line interface or integrated AI agent workflows.
JEVLAB ARTEnglishTypeSafe AIThis documentation defines the Description type alias within the TypeSafe AI SDK. It serves as a reference for developers to understand how criterion labels are structured, noting that a null value indicates an undescribed label.
JEVLAB ARTEnglishA developer project focused on bug-bounty chain tools, with Jev gating each step in the process.
JEVLAB ARTEnglishA moderation system for Mastra agents that processes inputs in a single file.
JEVLAB ARTEnglishThis project demonstrates an autonomous web browsing agent that integrates Jev for decision-making with Vercel's agent-browser for execution. It includes a benchmark to evaluate the system's performance in navigating and interacting with live websites.
JEVLAB ARTEnglishTypeSafe Jev playground — custom Choice/Score/Noul builder with live distributions.
JEVLAB ARTEnglishThis tool identifies breaking API changes by combining deterministic checks with TypeSafe JEV System One semantic analysis. It aims to detect inconsistencies often hidden within OpenAPI documentation prose to ensure better API reliability.
JEVLAB ARTEnglish
Max BladeThis project demonstrates an ambient assistant built with Jev that functions without a wake word. It utilizes probability-based analysis to identify user intent within continuous audio streams, aiming to create a more natural interaction model.
EnglishTypeSafe AIThis official resource provides a chronological record of updates and modifications to the TypeSafe SDK. It serves as a primary reference for developers to track version history and identify specific changes implemented in the platform.
JEVLAB ARTEnglishGuardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop.
JEVLAB ARTEnglish
CJ (Coding Garden)This project demonstrates a chat bot built with Jev that operates without a large language model. It provides immediate responses by directly integrating external tools like web search, Wikipedia, and weather data services.
English
SabrinaA demonstration of Jev's capability to quickly categorize a large volume of Hacker News posts.
English
Jiaqi GuThis project demonstrates an implementation of Jev for intelligent skill routing within an agent-based architecture. It showcases how community-driven development patterns can be applied to manage task distribution and decision-making processes in autonomous systems.
JEVLAB ART简体中文This project integrates Jev into the DeepSeek Harness framework. It demonstrates how developers can utilize Jev for automated judgment tasks within existing evaluation pipelines to streamline model assessment workflows.
JEVLAB ARTEnglishjcr is a developer tool designed to translate ambiguous agent prompts into precise, deterministic commands. It aims to enhance system reliability by ensuring that agent-driven tasks follow structured execution paths.
JEVLAB ARTEnglish
Sarvagya KulshreshthaThis project demonstrates an automated recruitment tool designed to evaluate candidate profiles against hundreds of companies. The creator claims the system generates compatibility confidence scores for 400 organizations within a twelve-second processing window.
EnglishThis repository provides a comprehensive tracker for the Jev ecosystem, documenting over 220 cases. It offers confidence-graded entries that are automatically rescanned every three hours and includes a guide for API access.
JEVLAB ARTEnglishThis project demonstrates the integration of TypeSafe Jev with Mobile MCP to facilitate structured control loops on Android devices. It provides a framework for developers to implement responsive agent-based interactions within mobile environments.
JEVLAB ARTEnglishThis project demonstrates an autonomous driving system that utilizes Jev to process real-time environmental data. The creator presents this simulation as a method for evaluating vehicle decision-making processes in dynamic driving scenarios.
EnglishEnd-to-end Jev-style structured-decision stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, preliminary RLCD, local serving, and interactive replay.
JEVLAB ARTEnglish
Alex NikolicThis project features an MLP trained on the Qwen 4B model to provide a typesafe alternative to Jev. It demonstrates how specialized architectural training can be applied to existing language models to achieve specific functional parity.
Englishs1-rs provides a typed System One layer for Rust, focusing on choice, scoring, and Noul mechanisms. This library demonstrates an architectural approach to integrating intuitive decision-making patterns directly into Rust applications through structured, type-safe abstractions.
JEVLAB ARTEnglishTypeSafe AIThis official TypeSafe AI reference guide demonstrates how to implement line-by-line semantic search functionality. It provides developers with the necessary patterns to perform precise text retrieval within structured datasets.
JEVLAB ARTEnglish
KaiA community post about using Jev to efficiently crawl job listings from company websites, significantly reducing time compared to an LLM.
EnglishTypeSafe AIThis official TypeSafe reference outlines the SDE cascade methodology. It demonstrates how to structure multi-stage AI workflows to improve output reliability and logical consistency during complex software development tasks.
JEVLAB ARTEnglishRoboJEV is a developer project demonstrating a two-stage Jev control system for a robotic arm within the MuJoCo simulation environment. It serves as an experimental implementation for testing hardware-focused control logic.
JEVLAB ARTEnglish
gokaygokayThis simulation game tasks players with managing a city built upon a whale. It demonstrates a decision-making framework integrated with GPT-6 Astra and H3 Max to maintain the survival of the settlement.
EnglishPydantic AI capabilities made stronger with Jev: small runnable demos, one file each.
JEVLAB ARTEnglish弈瞬：双 Jev 五子棋九宫格输入实验台，逐手查看模型决策，支持真实对局回放与实时对战。
JEVLAB ARTEnglishAn independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.
JEVLAB ARTEnglishThis project demonstrates a discriminative Monte Carlo Tree Search implementation. It utilizes TypeSafe Jev System One primitives integrated with Gemini to facilitate structured decision-making processes within an agentic framework.
JEVLAB ARTEnglish
NotteThis project demonstrates Jev, an agent designed to automate browser-based tasks. It functions by dynamically selecting and executing actions within a defined action space to navigate and interact with web interfaces.
EnglishA small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.
JEVLAB ARTEnglishjevymarket is an experimental trading bot for Polymarket that uses the Jev decision model to calculate probabilities. It combines web-based research with Jev's structured analysis to identify and execute trades based on configurable edges.
JEVLAB ARTEnglishEffect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.
JEVLAB ARTEnglishThis project demonstrates an application designed for rapid calorie tracking. The developer utilizes Jev to facilitate quick response times, aiming to streamline the user experience for logging nutritional intake through an automated interface.
Englishterrarium is a sandbox environment where a TypeSafe System One model operates a creature's controls. The project demonstrates how code-driven logic can be used to simulate and interact with a virtual world.
JEVLAB ARTEnglish
x.comJev is a System One model on OpenRouter that provides decisions with probabilities.
Englishblink is a tool that utilizes Jev technology to facilitate efficient codebase searching. It demonstrates how developers can integrate semantic search capabilities directly into their local development workflows for improved navigation.
JEVLAB ARTEnglishCommunity Go SDK for TypeSafe AI Jev / System One.
JEVLAB ARTEnglishThis project demonstrates the application of Jev for automated trading strategies. It provides a framework to backtest buy, sell, and hold decisions using NQ L10 order-book data to evaluate model performance in simulated market environments.
JEVLAB ARTEnglishThis project integrates Jev into application interfaces to provide smart autofill functionality. It demonstrates how automated suggestions can be implemented to streamline user data entry processes and improve overall interaction efficiency within digital forms.
EnglishRust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.
JEVLAB ARTEnglishJev is discussed with examples of Choice, Noul, and Score in a Python project.
JEVLAB ARTEnglishThis project demonstrates using Jev to enable real-time voice commands for browser navigation. The creator claims the system processes speech into actionable browser commands within 300 milliseconds while maintaining low operational costs.
EnglishThis project demonstrates one-pass option scoring using a local Gemma 3 4B model on Apple silicon via MLX. It includes a functional Doom demonstration to showcase the implementation of this specific scoring approach.
JEVLAB ARTEnglishScala 3 / ZIO client for the System One API: typed end-to-end, several questions per round-trip via NamedTuple.
JEVLAB ARTEnglishThis demonstration showcases Jido agents utilizing Jev to execute moves within a game of Tic-Tac-Toe. It serves as a practical example of how Jev can be applied to coordinate decision-making processes in multi-agent game environments.
EnglishBouncer is an agentic tool designed to enforce security policies by evaluating and judging tool calls made by Claude Code. It provides a mechanism for monitoring and restricting automated actions within the development environment.
JEVLAB ARTEnglish
Jozef GhermanA free AI tool built on Jev that quickly scans text for low-quality content, processing around 10,000 words in 2 seconds.
EnglishThis study from Boring Tools Kit examines SEO audit pricing. It demonstrates how Jev triage can be used to prioritize technical fixes and identify content gaps based on calibrated probability metrics for improved search performance.
JEVLAB ARTEnglishThis community project demonstrates the integration of Jev to operate a Tesla Full Self-Driving simulator. It provides a practical example of how Jev can be applied to control complex simulated environments for testing and development purposes.
EnglishThis experiment demonstrates the application of Jev to process a large personal writing archive. The author reports that the tool completed a comprehensive review of their entire body of work in under one second.
JEVLAB ARTEnglish
Submit a find
한국어
日本語
Español
Français
Deutsch
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
2
Agents & browsers
Decisions & routing
Research & data
Tools & apps
Games & real time
Start here
Creative & growth
Devices & robotics
Markets & experiments