The Jev launch post
Diogo 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.
A FIELD GUIDE TO JEV / VOL. 01
The best of Jev. Real projects, practical guides and ideas from across the internet.
Diogo 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 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 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.
TypeSafe 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.
Start with the Launch Post. Explore four official signals.
1,262 resources
AI-assisted summaries and translations. Check original sources for context and performance claims.
An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.
Jev PASSFIT 79%CAT 96%
This 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.
Source-linked curation
Code quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first.
Jev HOLDFIT 51%CAT 57%
YouWare 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.
Source-linked curation
A community experiment using Jev to analyze social media posts and determine effective content strategies.
Jev HOLDFIT 63%CAT 43%
decido is a Python library designed for making probabilistic decisions. It supports integration with Jev or custom providers and utilizes Playwright for web crawling tasks to facilitate automated decision-making workflows.
Source-linked curation
This research project investigates the practical utility of Jev confidence scores during task execution. It provides a framework for developers to assess how these metrics correlate with model performance in real-world scenarios.
Source-linked curation
Jevinik is a stock evaluation tool that utilizes Jev to facilitate rapid market analysis. The project demonstrates how automated processing can be applied to financial data to assist users in evaluating market trends and research.
Source-linked curation
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.
Source-linked curation
This project features a real-time Tetris implementation where Jev-based agents compete against other AI models. It demonstrates game logic integration and multi-agent interaction within a competitive environment.
JEVLAB ARTSource-linked curation
This resource demonstrates the use of Jev for real-time coaching support. It highlights how the tool assists users in identifying and correcting errors or inconsistencies during writing sessions to improve overall quality.
Source-linked curation
TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.
Jev PASSFIT 77%CAT 99%
Short practical intro with a Python ticket-triage example.
Jev HOLDFIT 75%CAT 62%
SuperX integrates with Jev to automate content evaluation. The creator claims the tool analyzes 61 distinct questions per post in under one second to estimate viral potential.
Jev HOLDFIT 63%CAT 90%
This community project demonstrates the potential of Jev to function as a computing environment by emulating a 6502 processor. It serves as an experimental proof-of-concept for running legacy hardware architectures within the Jev framework.
Source-linked curation
Jev conducts a sentiment-based stock market analysis for the Danish market in 2025, using diverse data sources with low cost.
Jev HOLDFIT 52%CAT 99%
DGUI-HyperMem (DeckerGUI HyperMemory) - self-hosted hybrid memory MCP server on Cloudflare Workers with a JEV (Choice/Noul/Score) reasoning layer and a HuggingFace training-brain flywheel.
Jev HOLDFIT 65%CAT 41%
jlink provides a framework for linking data records using plain-English matching rules. It utilizes Jev Noul pair judgments to perform local candidate blocking and automated match resolution for record linkage tasks.
Source-linked curation
CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI.
Jev HOLDFIT 65%CAT 55%
jevscape provides a RuneBench harness for Jev, featuring a bounded action catalog and a tick-mode controller. It includes a live dashboard designed to help developers monitor and manage agentic workflows within the Jev ecosystem.
Source-linked curation
This project demonstrates a Snake game implementation where movement is controlled by parallel Jev assessments. It showcases a specific architectural pattern using one API call per game tick to manage the snake's directional logic.
Source-linked curation
This open-source project introduces a routing mechanism for Claude Code. It demonstrates how to prioritize frequently used skills through Jev integration to improve task selection efficiency.
Source-linked curation
This Scala 3 client for the System One API provides an effect-agnostic interface compatible with various sttp backends. It enables developers to integrate Jev services using their preferred effect systems while ensuring type-safe handling of question values.
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.
Jev PASSFIT 79%CAT 99%
Ultra-fast model routing using Jev for agent-based systems.
JEVLAB ART
Jev HOLDFIT 43%CAT 72%
Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev.
Jev HOLDFIT 66%CAT 33%
This repository provides a curated collection of software utilities designed for Jev, the TypeSafe AI System One model. It serves as a central directory for developers seeking tools to implement typed decision-making workflows within their own AI-integrated projects.
Source-linked curation
This Go-based CLI and single-binary MCP server integrates TypeSafe judgments directly into Claude Desktop, Claude Code, and Codex environments. It demonstrates a method for bridging formal verification outputs with LLM-based coding assistants for improved workflow reliability.
JEVLAB ARTSource-linked curation
Semantic SQL for Postgres, powered by Jev.
Jev HOLDFIT 68%CAT 84%
This project demonstrates the application of Jev to predict human move patterns in a game of rock-paper-scissors. The creator claims the system identifies behavioral trends to anticipate player choices during competitive play.
Source-linked curation
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.
Source-linked curation
Jev controls both hands and fingers to play piano in real-time based on visual input.
Jev HOLDFIT 56%CAT 64%
Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.
Jev HOLDFIT 55%CAT 84%
This project provides a compact, extensible harness designed to facilitate decision-to-action workflows within TypeSafe Jev environments. It serves as a utility tool for developers looking to streamline automated logic execution.
JEVLAB ARTSource-linked curation
This official TypeSafe AI reference explains techniques for structure recovery. It demonstrates how to reliably parse and format unstructured model outputs into consistent, machine-readable data structures for downstream application integration.
Jev HOLDFIT 85%CAT 57%
This project demonstrates an automated agent designed to streamline second-hand product discovery. The creator claims the system evaluates listings at a rate of 26 items per minute to assist users in making faster purchasing decisions.
Jev HOLDFIT 17%CAT 93%
This project demonstrates a predictive launcher powered by Jev. It aims to anticipate user intent by analyzing typing patterns to streamline navigation and task execution within the interface.
Jev HOLDFIT 59%CAT 70%
This extension for Pi coding agents implements TypeSafe Jev validation for tool interactions. It provides automated security checks including prompt injection detection, secret scrubbing, and task pinning to improve the reliability of agentic workflows.
Source-linked curation
s1s is a search tool designed to help developers navigate and trace codebases. It utilizes TypeSafe judgments and repository evidence to assist in understanding complex project structures and relationships.
Source-linked curation
Grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.
Jev PASSFIT 72%CAT 71%
mimicry is a tool designed to rewrite AI-generated drafts to match a specific personal voice. It utilizes a bounded TypeSafe feedback loop to maintain consistency and control throughout the text refinement process.
Source-linked curation
This repository provides a Go SDK for interacting with the TypeSafe AI API. It enables developers to integrate TypeSafe AI functionality directly into Go applications by providing structured client methods for API communication.
Source-linked curation
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
Jev HOLDFIT 71%CAT 43%
A tool developed using Jev to create a voice builder for Youform, noted for its speed.
Jev HOLDFIT 61%CAT 66%
This project demonstrates a hybrid coding architecture where a deliberative System 2 handles complex logic while a Jev-based System 1 manages rapid, reflexive execution. It explores balancing high-level reasoning with immediate, automated responses in software development.
Source-linked curation
This GitHub Action utilizes Jev to automate the triage and classification of pull requests. It demonstrates how developers can integrate automated decision-making workflows directly into their repository management processes to streamline code review tasks.
JEVLAB ARTSource-linked curation
This tool automates pull request analysis by evaluating code against Clean Code principles. It utilizes Jev for assessment and Luna for review, providing structured feedback on code quality within a Next.js framework.
Source-linked curation
This demonstration showcases Jev processing a large volume of advertising data. The creator claims the system can handle nearly two thousand ads in under twenty seconds, suggesting potential for high-speed market analysis workflows.
Jev HOLDFIT 14%CAT 41%
This video guide explores the core capabilities of Jev, demonstrating how it handles browser automation, data classification, and code review tasks without relying on traditional large language models.

Jev HOLDFIT 49%CAT 48%
This gaming project demonstrates a mechanism for toggling between manual control and AI-driven gameplay. It showcases how Jev can be integrated into interactive environments to facilitate real-time transitions between human input and automated agent decision-making.
Source-linked curation
This demonstration explores using inference engineering and scoring endpoints to guide open source models toward Jev-style decision-making. The creator showcases a workflow for implementing these behavioral adjustments within the model architecture.
Jev HOLDFIT 46%CAT 88%
This browser extension utilizes Jev to analyze and classify online articles. It demonstrates how to automatically identify news framing, content topics, and the presence of loaded language within web-based media.
Source-linked curation
Local Telegram channel JSON analyzer for intent, quality, sentiment, and speaker tone.
Jev HOLDFIT 23%CAT 59%
Run a JSON Schema through TypeSafe's Jev API, and get JSON back.
Jev PASSFIT 75%CAT 78%
A community post details a Pac-Man game where every move is determined by Jev, offering strategic insights.
Jev HOLDFIT 62%CAT 99%
This 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.
Source-linked curation
A community post explaining Jev as an AI for decision-making, faster and cheaper than frontier LLMs.
Jev HOLDFIT 51%CAT 84%
This browser-based tool simplifies creating requests for TypeSafe Jev by providing a template-driven interface. It allows users to fill in required fields locally without needing JSON knowledge or software installations, streamlining the request generation process.
Source-linked curation
This 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.
Jev HOLDFIT 62%CAT 67%
This project demonstrates a playful application of Jev technology to generate randomized responses to user inquiries. It functions as a digital novelty tool, showcasing how Jev can be integrated into interactive, decision-making interfaces for casual entertainment purposes.
Source-linked curation
Jev is integrated with Cloudflare AI Gateway to provide structured answers to typed questions.
Jev HOLDFIT 67%CAT 62%
This official TypeSafe reference defines the Score primitive. It explains the core mechanics for evaluating model outputs within the TypeSafe framework, providing developers with the necessary technical specifications for implementation.
Jev PASSFIT 87%CAT 91%
An agent using headless Chromium to quickly navigate the web, demonstrated by browsing Wikipedia links efficiently.
Jev HOLDFIT 12%CAT 92%
switchloom is a deterministic model routing system designed for coding agents. It demonstrates a specialized mechanism for managing model selection, specifically highlighting capabilities related to Codex integration for automated programming tasks.
JEVLAB ARTSource-linked curation
1v1 Jev quickscope arena — Three.js + TypeSafe System One.
Jev PASSFIT 79%CAT 98%
This 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.
Jev HOLDFIT 59%CAT 98%
A community project using Jev to customize Hacker News content preferences.
Jev HOLDFIT 47%CAT 44%
This project demonstrates a massively parallel browser-based testing suite designed for adversarial evaluation of software releases. The creator claims this approach enables cost-effective automated testing by running multiple browser instances simultaneously to identify potential vulnerabilities.
Source-linked curation
This resource explores the use of Jev as a tool for language generation. It highlights community perspectives on the platform's potential and challenges existing assumptions regarding its functional capabilities in text synthesis.
Source-linked curation
This video guide demonstrates how to utilize the Jev architecture to construct various software applications. It provides a practical overview of the development workflow and capabilities available within the Jev ecosystem for creators.

Jev HOLDFIT 42%CAT 49%
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.
Jev HOLDFIT 82%CAT 53%
A Codex plugin that uses Jev to streamline and reduce excessive tool outputs.
JEVLAB ART
Jev HOLDFIT 63%CAT 80%