JEVThe best of Jev. Real projects, practical guides and ideas from across the internet.
Updated 22 Resources
What’s new
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.
This project integrates Jev into the classic Chrome Dino game to provide real-time decision scoring. It demonstrates how external logic can influence gameplay mechanics by displaying live evaluation metrics during the runner sequence.
English
JEVLAB ARTjev-agent-browser provides a bounded execution environment for browser agents by integrating Jev with agent-browser. It enables typed action selection and structured task orchestration, allowing parent agents to delegate specific web navigation and research tasks safely.
JEVLAB ARTThis project demonstrates a method for verbatim context compaction using TypeSafe Jev decision-making. It provides an experimental approach to optimizing data processing within Jev-based agent architectures.
EnglishThis video demonstration compares Jev against a Qwen-based structured-output LLM baseline running on Cerebras hardware. It provides a visual side-by-side assessment of how each model handles structured data generation tasks in a real-time environment.
English
JEVLAB ARTThis Rust-based CLI tool utilizes Jev to evaluate and rank agent skills based on real-time session context. It demonstrates integration with Claude Code and supports structured JSON outputs for decision-making processes.
English
JEVLAB ARTThis Chrome extension integrates with X to label posts using Jev judgments. It demonstrates a method for real-time content analysis and provides a live counter to track associated processing costs while browsing.
EnglishCorent demonstrates a model routing system that utilizes Jev to evaluate prompts and quality requirements. This approach aims to dynamically select the most appropriate AI model for specific tasks before generating the final output.
EnglishJEVLAB ARTThis repository provides TypeScript-based experiments and evaluations for the Jev model. It serves as a technical resource for developers to analyze model performance and latency through structured benchmarks and testing frameworks.
EnglishTypeSafe AIThis function enables developers to generate structured evaluation questions using an ordered rubric. It demonstrates how to define specific scoring criteria for model outputs within the TypeSafe AI SDK framework.
JEVLAB ARTEnglish
JEVLAB ARTThis project introduces a System One-style model fine-tuned from Qwen3.5-2B. It demonstrates a method for performing single-pass typed decision-making tasks while incorporating calibrated probability outputs for improved reliability in automated reasoning workflows.
EnglishJEVLAB ARTThis project provides a personal assistant agent built on Vercel's eve. It utilizes 100 mocked tools to compare the efficiency of Jev versus standard LLM tool selection processes by measuring the number of steps required for task completion.
EnglishThis tool provides near-real-time scoring for social media hooks by evaluating them against approximately 100 distinct personas. It demonstrates a method for creators to test content performance across diverse audience segments.
English
JEVLAB ARTThis repository provides an MCP server implementation that exposes TypeSafe System One judgments, including noul, choice, and score, as functional tools for AI agents. It demonstrates how to integrate structured judgment data into agentic workflows.
English
JEVLAB ARTThis project integrates the Jev System One model into Home Assistant to function as a conversation agent. It demonstrates how to connect external language models to home automation interfaces for voice-based control.
English
JEVLAB ARTThis 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.
EnglishJEVLAB ARTThis tool utilizes an LLM to filter Android notifications and SMS by identifying noise rather than relying on keyword matching. It processes verification codes locally to ensure privacy while allowing uncertain messages to pass through.
EnglishTypeSafe AIThis TypeSafe AI guide demonstrates systematic methods for verifying the accuracy of citations generated by LLMs. It provides essential workflows to ensure that referenced sources are authentic and correctly attributed within AI-assisted research tasks.
JEVLAB ARTEnglishJEVLAB ARTThis repository provides a collection of Shadcn-style reusable components and interface blocks designed for TypeSafe AI integration. It demonstrates how to implement consistent UI patterns for AI-driven applications using established design standards.
EnglishJEVLAB ARTjeff is a self-hosted alternative to TypeSafe's jev platform. This project utilizes GliFormer to provide drop-in functionality for users seeking to manage their own instances of the service.
EnglishJEVLAB ARTThis 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.
English
Chandramouly KandacharThis demonstration showcases Jev controlling both hands and fingers to play a piano in real-time. The system processes visual input to coordinate complex movements, illustrating the agent's capability for responsive, multi-limb musical interaction.
EnglishTypeSafe AIThis official TypeSafe resource provides a structured guide for implementing skill suggestion mechanisms within AI agents. It demonstrates how to dynamically recommend relevant capabilities to users to enhance interaction efficiency and task completion.
JEVLAB ARTEnglish
JEVLAB ARTThis plugin integrates TypeSafe Jev System One decision tools into the Hermes Agent framework. It provides specific functions for checking, routing, scoring, and evaluating agent decisions to improve operational logic and reliability within the system.
English
JEVLAB ARTThis 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.
English
JEVLAB ARTThis community-developed Go SDK provides an interface for the TypeSafe System One API. It features typed support for Choice, Score, and Noul questions, while incorporating built-in mechanisms for request retries, context management, and structured error handling.
EnglishJEVLAB ARTego-jev provides an inner loop for ego lite using TypeSafe System One. It replaces standard LLM turns with a single typed decision per DOM step, aiming to improve browser agent performance by reducing latency during interactive web tasks.
English
JEVLAB ARTjot is a general-purpose System One agent designed for the Jev ecosystem. This project provides a framework for autonomous task execution and serves as an implementation example for developers building within the Jev environment.
EnglishThis experiment demonstrates Jev successfully navigating the Elite Four in Pokémon FireRed. The creator reports that the agent completed the challenge using low-cost computational resources, showcasing its ability to handle complex game mechanics.
EnglishThis experiment tests Jev's ability to generate visual content on a pixel canvas. The demonstration shows that the model currently struggles to produce recognizable imagery, highlighting specific limitations in its spatial generative capabilities.
EnglishTypeSafe AIThis documentation defines the AuthenticationError class within the TypeSafe AI JavaScript SDK. It details how the class handles HTTP 401 errors, including inherited properties like status codes, response bodies, and request identifiers for debugging API interactions.
JEVLAB ARTEnglish
Mau BaronThis demonstration shows Jev autonomously controlling multiple characters within a video game environment. The creator showcases the system's ability to execute rapid, real-time decision-making during competitive gameplay scenarios.
EnglishThis tool demonstrates a method for detecting the end of voice-dialogue turns. It utilizes Jev scores processed immediately following speech input to determine when a user has finished speaking, facilitating more natural conversational flow in interactive avatar systems.
EnglishTypeSafe 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 ARTEnglishJEVLAB ARTThis cyberpunk-themed game uses TypeSafe Jev to simulate a tense border crossing encounter. Players must navigate dialogue choices to bluff guards and verify digital receipts to progress through the narrative.
EnglishThis tool utilizes Jev to analyze user session replays for identifying software defects. It demonstrates an automated workflow designed to generate bug fix pull requests, aiming to streamline the debugging process for development teams.
EnglishThis project integrates three Jev-powered agents into a first-person shooter environment. It demonstrates multi-agent coordination within a real-time combat setting, showcasing how Jev models can function as autonomous players in competitive gaming scenarios.
EnglishTypeSafe AIThis official TypeSafe documentation defines the concept of agent skills. It explains how modular capabilities are structured to enable autonomous agents to perform specific tasks effectively within the TypeSafe AI framework.
JEVLAB ARTEnglish
JEVLAB ARTThis project demonstrates a method for integrating Jev agent skills into the Oxlint static analysis framework. It provides a technical implementation for extending linting capabilities through custom plugins designed to leverage Jev-based logic.
EnglishThis project demonstrates a method for filtering social media content by leveraging user bookmarks. It utilizes Jev analysis to curate a personalized feed, aiming to improve relevance by prioritizing content that aligns with individual user interests and saved items.
EnglishThis research demonstrates how Jev AI automates quality assurance for physical AI training datasets. It showcases a method for verifying action labels at scale to improve the reliability of robotic learning models.
EnglishTypeSafe AIThis TypeSafe AI guide demonstrates how to implement classification tasks by leveraging confidence scores. It explains the methodology for evaluating model output reliability to improve decision-making accuracy in automated classification workflows.
JEVLAB ARTEnglishJEVLAB ARTThis project demonstrates an approach to controlling the original StarCraft shareware using TypeSafe Jev. It utilizes keyboard and mouse input emulation based on recorded action probabilities to interact with the game environment.
EnglishJEVLAB ARTjevball is a 3D football simulation where each player operates as an independent Jev decision-making agent. The project demonstrates multi-agent coordination in a sports context, allowing users to observe autonomous gameplay or manually control a specific player.
EnglishThis project showcases an experimental trading system that utilizes Jev to enforce defined rules for automated decision-making. The creator demonstrates how structured logic can be applied to market analysis within a typed framework.
English
JEVLAB ARTThis repository provides a visual Jev laboratory environment designed for testing and interacting with various game and emulator platforms. It serves as a practical resource for developers exploring Jev-based integration within gaming software architectures.
EnglishJEVLAB ARTThis Next.js application serves as a sandbox for testing the Jev model, specifically the System One architecture. It provides a practical interface for developers to experiment with model outputs and explore TypeSafe AI integration capabilities.
EnglishJEVLAB ARTThis experimental project demonstrates a multi-horizon signal generator for Bitcoin. It utilizes TypeSafe Jev probabilities alongside real-time Binance market data to explore potential price trend indicators within a technical analysis framework.
EnglishJEVLAB ARTjevchat is a research-oriented chatbot project designed to process and respond to user-typed inquiries. This repository serves as a functional demonstration of conversational interaction patterns within a broader collection of experimental language processing tools.
English
JEVLAB ARTThis project demonstrates an experimental application of TypeSafe Jev for the rapid analysis of financial news and market tickers. It serves as a practical exploration of how Jev-based workflows can be utilized to streamline information processing.
EnglishJEVLAB ARTJevGuard is a developer utility designed for decision runtime environments. It features zero-token caching and a calibration mechanism to assist in managing and optimizing AI-driven decision processes.
EnglishJEVLAB ARTOpenJev is an open-source initiative by SiliconLabAI focused on the development of a Jev-class decision model. This project serves as a research-oriented resource for exploring architectural approaches to autonomous decision-making systems.
English
JEVLAB ARTThis MCP server integrates TypeSafe Jev capabilities into agent workflows. It provides structured methods for classifying, scoring, and screening data, aiming to deliver verifiable confidence levels for each automated response generated by the system.
EnglishJEVLAB ARTjev-me provides an interactive interrogation tool where Jev analyzes and challenges your project ideas. It functions as a structured brainstorming assistant designed to stress-test concepts through critical questioning and logical evaluation.
English
Niaz MorshedThis experimental plugin for coding agents utilizes Jev to deliver automated quality feedback during the development process. It demonstrates a local-first approach to improving code standards within agentic workflows.
EnglishThis project evaluates Jev for converting free-text player intent into structured server actions. The creator reports a 96% agreement rate and a 317 ms median latency for these automated mappings within a tabletop gaming context.
JEVLAB ARTEnglishYouWare is a recruitment tool designed to automate the evaluation of job applications. The developer claims the system can process 360 résumés in under 25 seconds while providing automated scoring for candidates.
English
JEVLAB ARTThis project demonstrates using Jev as a judgment sensor within a builder-agent loop. It illustrates a workflow where priors and probabilities are processed to determine the next action for an autonomous agent.
English
JEVLAB ARTjevkit is a Rust-based command-line interface designed for TypeSafe Jev. It enables users to perform offline linting and manage typed decisions, aiming to validate configurations before execution.
English
JEVLAB ARTThis tool functions as a mahjong assistant that utilizes Jev to provide tile discard suggestions. It is designed to help players improve their decision-making process during games by offering strategic guidance in Japanese.
EnglishJEVLAB ARTThis community node integrates the TypeSafe AI System One API into n8n workflows. It enables developers to implement typed yes/no, choice, and scoring tasks that utilize calibrated probability outputs for structured decision-making.
EnglishJEVLAB ARTThis community-maintained Go SDK provides a structured interface for the TypeSafe AI System One evaluation API. It features fluent builders, typed question definitions, and built-in retry logic with exponential backoff to facilitate reliable interaction with the evaluation service.
JEVLAB ARTThis project provides a semantic code search and diff auditing tool for AI coding assistants like Antigravity, Cursor, and Claude Code. It utilizes TypeSafe System One to help developers verify code changes and improve search efficiency within their development workflows.
EnglishJEVLAB ARTThis tool utilizes Jev Choice and Noul logic to perform technical analysis on A-share stocks. It evaluates market direction and volatility across two time horizons to provide Buy, Hold, or Sell assessments without executing actual trades.
English
JEVLAB ARTThis repository provides a Go client library for interacting with the TypeSafe API. It is designed to assist developers in integrating TypeSafe functionality directly into their Go-based applications and tooling workflows.
English
Marcel PociotThis browser extension by Marcel Pociot demonstrates a method for filtering social media content. It uses Jev-based judgment to automatically collapse posts on X based on user-defined natural language criteria for a more curated feed.
EnglishJEVLAB ARTThis Chrome extension utilizes Jev to analyze web pages for commercial intent or firsthand reporting. It marks Google search results with existing verdicts or snippet-based estimates, while leaving low-confidence entries undecided to help users distinguish content types.
English
Riley BrownThis project demonstrates Jev processing 500 emails for a total cost of 3.5 cents. The creator claims this workflow highlights the platform's efficiency in handling high-volume classification tasks at a low price point.
EnglishJevals provides a local testing environment designed for evaluating Jev requests. The project demonstrates how users can refine and improve their output quality by applying specific primitive operations within a controlled development workflow.
English
JEVLAB ARTThis project provides a native macOS menu bar application for Notion. Built with Swift and SwiftUI, the tool aims to offer a lightweight interface for accessing Notion workspaces directly from the system menu bar.
English
fatwang2Jev Search is an open-source tool that utilizes Jev and external search APIs to process plain language queries. This project demonstrates a method for integrating natural language processing into search retrieval workflows.
JEVLAB ARTEnglishFocus Rail showcases a simulation game where Jev manages real-time train routing to stations. The creator demonstrates how the system handles complex pathing logic without relying on a traditional solver.
JEVLAB ARTEnglishJEVLAB ARTPlayJev demonstrates a 0.8B parameter model capable of playing ten browser games. The system operates by calculating move probabilities in a single forward pass without generating text, showcasing a specialized approach to game-playing agents.
English
Submit a find
한국어
日本語
Español
Français
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
Games & real time
6
Agents & browsers
Creative & growth
Decisions & routing
Research & data
Start here
Tools & apps
Markets & experiments