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.
JEVLAB ARTThis 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.
English
Zahle KhanJev board is a tool designed for ambient intelligence interfaces. It demonstrates the integration of fast, reliable models to facilitate responsive user interactions within a generative UI framework.
English
JEVLAB ARTThis tool integrates Jev-powered ranking into zsh shell history. It demonstrates how to provide Fish-style autosuggestions by leveraging TypeSafe AI to prioritize command history based on user context and relevance.
EnglishThis project demonstrates Jev playing Tetris by executing real-time block placement decisions. It showcases the application of Jev-based logic in a classic arcade environment to manage game state and piece movement dynamically.
English
JEVLAB ARTThis repository provides an unofficial Go SDK designed to facilitate integration with the TypeSafe AI Jev API. It serves as a developer tool for implementing Jev-based functionality within Go applications.
English
JEVLAB ARTThis project demonstrates an implementation of Typesafe.AI to automate the generation of code diff reviews. It provides a workflow for integrating AI-driven analysis into version control processes to assist developers in evaluating code changes.
EnglishThis demonstration showcases Jev performing automated classification, priority assessment, spam detection, and reply prediction tasks. The creator reports testing these capabilities across a dataset of 1,000 emails to evaluate the system's functional performance in managing inbox workflows.
English
JEVLAB ARTThis repository provides Go utilities for the TypeSafe API, including a natural language grep-like CLI, a Kubernetes log analysis plugin, and a standard-library-only SDK. It demonstrates how to integrate TypeSafe services into Go-based workflows for automated data querying and log inspection.
JEVLAB ARTJevmoji is a tool that uses TypeSafe's Jev model to score and retrieve relevant emojis based on user input. It demonstrates how to integrate AI-driven semantic scoring with local keyword matching for emoji discovery.
JEVLAB ARTThis independent research report examines a non-verbal model developed by the creators of RLHF. It provides a 52-page document, 50 Chinese-language reproduction tests, and a comprehensive data table for technical analysis.
English
AnushaMagic Jev Ball is a tool designed to streamline GitHub pull request workflows. It utilizes Jev to evaluate CI status, diff size, and existing reviews, aiming to provide automated approval decisions within a reported timeframe of 200 milliseconds.
EnglishJEVLAB ARTThis proof-of-concept demonstrates using TypeSafe Jev to automate Hermes Agent command approvals. The creator claims improved efficiency metrics compared to standard methods based on tests conducted across 153 real-world command scenarios.
English
JEVLAB ARTTypeAR is a decoding engine for autoregressive LLMs that implements a type-safe, one-decision-per-token approach. Inspired by Jev, the project demonstrates a methodology for enforcing structural constraints during the generation process.
English
JEVLAB ARTThis project provides a guardrail and model router for LLM gateways using TypeSafe's Jev System One model. It demonstrates how to implement independent evaluation metrics for accuracy, calibration, and latency using standard Python libraries.
EnglishTypeSafe AIThis documentation defines the WithResponse interface for TypeSafe AI, which structures parsed data alongside its associated HTTP response and request ID. It provides developers with a standardized way to access response metadata and body content within the SDK.
JEVLAB ARTEnglish
JEVLAB ARTjevymarket 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.
EnglishTypeSafe AIThis official documentation defines the concept of state within the TypeSafe AI framework. It explains how state management functions as a core component for maintaining consistency and context across complex AI interactions and system workflows.
JEVLAB ARTEnglishJEVLAB ARTThis project demonstrates a method for querying local LLMs on Apple Silicon to receive calibrated probabilities rather than raw text. It aims to provide structured output directly, bypassing the need for traditional text generation or subsequent parsing steps.
EnglishThis demonstration shows Jev engaging with the classic arcade game Time Crisis. The setup utilizes a physical harness system to assist with aiming and movement, showcasing how hardware integration can influence gameplay performance in a retro arcade environment.
EnglishJEVLAB ARTThis repository provides Jev judgments for Agent Zero, incorporating typed tools and probability cards. It demonstrates a framework for enhancing agent reliability through structured type-safe interactions and probabilistic decision-making processes.
English
IzzuddinThis experiment showcases Jev navigating the Pokémon Showdown interface to make strategic battle decisions. The creator demonstrates how the model handles real-time game logic, though performance varies during competitive play.
EnglishJEVLAB ARTThis project presents a tactical cyberpunk arena combat game. It demonstrates the integration of the TypeSafe AI Jev System One decision model to manage gameplay mechanics and strategic AI behaviors.
English
JEVLAB ARTThis tool provides automated feedback on academic papers. It demonstrates a workflow for rapid document review, allowing users to receive structural and content-related insights shortly after submission.
EnglishJEVLAB ARTThis community-maintained PHP SDK provides a client for the TypeSafe AI System One API. It enables developers to perform typed queries, manage asynchronous requests via Guzzle promises, and handle model discovery with configurable retries and logging.
JEVLAB ARTThis experimental framework utilizes JEV to analyze structured market data for short-term stock price forecasting. It serves as a technical demonstration of applying JEV-based logic to financial trend prediction models.
English
JEVLAB ARTThis developer tool manages rule selection for Claude to filter and display only relevant information. It demonstrates a method for streamlining AI interactions by dynamically applying context-specific constraints to improve output focus.
EnglishJEVLAB ARTThis demonstration showcases how Jev can track and respond to user sentiment over time. It utilizes structured state management to maintain a persistent mood profile based on the tone of ongoing interactions.
EnglishJEVLAB ARTThis resource by Leonardo Bissoli explores the application of Jev for structured decision-making processes. It provides a video overview and reference materials to demonstrate how Jev can be utilized to organize and execute complex logical workflows in practical scenarios.
Português
SachinThis demonstration explores multi-agent interaction by placing Jev instances into a game of Catan. It highlights the challenges these agents face when attempting to navigate complex social negotiation and strategic resource trading within a competitive board game environment.
EnglishThis creative project utilizes Jev and browser automation tools to generate digital artwork. It demonstrates a workflow for producing a painting of the Golden Gate Bridge through integrated software processes.
English
JEVLAB ARTThis project demonstrates an agent playing browser-based table tennis. It showcases the use of structured telemetry and typed decision-making processes to interact with standard web inputs while maintaining auditable evidence of its actions.
EnglishWorth Replying is a community tool that utilizes Jev to identify relevant X discussions. It aims to assist users in finding meaningful opportunities for business outreach and engagement within the platform.
English
JEVLAB ARTThis developer project demonstrates an agentic approach to web navigation where Jev selects actions while an LLM handles planning and source citation. It serves as an experimental framework for automating browser-based tasks through structured reasoning.
EnglishJEVLAB ARTThis plugin integrates the Jev System One architecture with QuantumNous new-api. It enables native v1/systemone endpoint support, facilitating synchronous evaluation processes and automated token billing for AI tasks.
English
DuncanThis demo by Ephraim Duncan showcases a routing system built with Jev. It illustrates how the framework can be used to dynamically determine which AI model should process a specific incoming request.
EnglishJEVLAB ARTego-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.
简体中文
JEVLAB ARTjevprune is a utility designed to filter command-line output for coding agents. It uses specific task descriptions to help agents focus on relevant information by pruning unnecessary data from terminal streams.
EnglishJEVLAB ARTThis project provides a Jev-powered browser MCP designed for LLM agents. It demonstrates a method for browser interaction that aims to bypass LLM token usage for decision-making, with the creator claiming response times around 300ms.
English
x.comThis resource introduces Jev, a System One model available on OpenRouter. It demonstrates how the model generates decisions accompanied by associated probability metrics, offering a structured approach to automated reasoning and output evaluation within the platform environment.
English
JEVLAB ARTThis resource outlines the Jev Engineering methodology, a structured approach designed for the development of AI agents. It explains the core principles and systematic practices intended to improve the reliability and functional design of autonomous systems.
English
AbolThis project demonstrates a workflow using Jev to process and analyze financial news for potential investment insights. It highlights how automated editorial summarization can assist users in identifying market opportunities from large volumes of incoming data.
EnglishJEVLAB ARTThis tool enables Claude Code to select appropriate installed skills for a session. It utilizes Jev for decision-making processes and integrates with skills.sh to facilitate the discovery of available capabilities.
EnglishJEVLAB ARTThis Python package utilizes typesafe.ai to evaluate code comments based on specific heuristics. It demonstrates an automated approach to assessing documentation quality within a codebase by applying structured analysis to developer-written comments.
English
JEVLAB ARTThis research project presents an English–Icelandic dictionary application. It demonstrates the use of Jev to rerank search results, aiming to improve the accuracy and relevance of the dictionary entries provided to users.
EnglishJEVLAB ARTThis discussion explores the architectural trade-offs between using typed decision logic and LLM-based inference for classification, routing, and scoring tasks. Participants debate the reliability and efficiency of replacing probabilistic model calls with structured, deterministic decision-making processes.
EnglishThis 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.
JEVLAB ARTEnglishThis project demonstrates the use of Jev to conduct a musical orchestra in real time. The creator showcases a technical experiment where the system interprets and manages musical performance inputs to guide the ensemble.
EnglishThis experiment demonstrates the use of Jev to transform simple English input into elaborate prose in real-time. It showcases a creative writing tool designed to assist authors by dynamically enhancing their text as they type.
EnglishJEVLAB ARTThis project demonstrates how to use Jev and Symfony AI to automatically categorize public support requests. It showcases asynchronous processing, rate limiting, and real-time dashboard updates using Symfony components to classify intent, urgency, and bug reports.
English
JEVLAB ARTThis 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.
EnglishJEVLAB ARTThis project provides a framework for intelligent model routing, incorporating caching mechanisms and failover strategies. It demonstrates a technical approach to managing request distribution across multiple Jev-based model endpoints to improve system reliability and efficiency.
English
x.comThis collection highlights 19 open-source projects utilizing Jev technology. It demonstrates diverse practical applications, ranging from autonomous AI agents to interactive game mechanics, providing a broad overview of how developers are currently integrating Jev into their software ecosystems.
简体中文This community experiment showcases Jev interacting with the platformer game Geometry Dash. It demonstrates the model's ability to process visual gameplay input and execute corresponding control commands within a real-time gaming environment.
EnglishJEVLAB ARTThis repository provides a collection of experimental demonstrations designed to evaluate the functionality of the Jev System One Model. It serves as a practical resource for testing the model's performance and behavior in various scenarios.
EnglishJEVLAB ARTjselect provides a utility for filtering source-linked evidence while adhering to specific token constraints. It utilizes Jev Noul relevance judgments and local diversity-aware selection methods to prioritize relevant information for AI processing.
EnglishTypeSafe AIThis official reference guide outlines the implementation steps for the TypeSafe AI Python SDK. It provides developers with the necessary instructions to integrate and utilize the library within their local environments for structured AI interactions.
JEVLAB ARTEnglishJEVLAB ARTThis project compares Jev against Gemini 3.8 Flash by labeling 1,000 app reviews. The creator claims the Jev implementation achieves significantly faster processing speeds and lower costs compared to the Gemini model in this specific task.
EnglishJEVLAB ARTThis project demonstrates fine-grained robot control using Jev. It provides physics-based previews and configurable tasks within the LIBERO framework to help users experiment with robotic manipulation and simulation environments.
EnglishThis community experiment evaluates Jev's capabilities within a browser-based automation environment. The creator reports observing functional limitations after the agent completes five consecutive actions, providing a practical look at current operational constraints for this specific implementation.
EnglishTypeSafe AIThis pattern demonstrates a method for routing requests based on model confidence scores. It teaches how to implement conditional logic to ensure higher quality outputs by directing tasks to appropriate processing paths.
JEVLAB ARTEnglish
JEVLAB ARTPort Cleanup is a macOS utility designed to assist users in identifying and terminating active network ports. This tool provides a streamlined interface for managing local port processes, helping developers maintain a clean development environment by safely stopping unnecessary services.
EnglishJEVLAB ARTThis project replaces Claude Sonnet with Jev for decision-making in OpenPoke. It provides an A/B comparison framework and includes results from an adversarial test run involving over 43,000 requests to evaluate the injection gate performance.
EnglishJEVLAB ARTThis macOS menu-bar application translates spoken commands into structured actions using Jev, a System One model that provides typed decisions rather than generated text. It combines deterministic local execution with AI-guided UI interaction to control applications and system settings.
English
OskarThis project introduces a framework for executing end-to-end software tests using autonomous agents powered by Jev. It demonstrates how agentic workflows can be integrated into testing pipelines to automate complex validation tasks.
English
Milind SoniTipTour is an open-source AI-driven pointer assistant for macOS. It demonstrates how to integrate Jev or Gemini Live to enable cursor control through local processing, offering users a hands-free navigation experience on their desktop environment.
JEVLAB ARTEnglishJEVLAB ARTThis repository provides a Swift SDK designed for integration with TypeSafe AI. It serves as a developer tool to facilitate communication and data handling within the TypeSafe ecosystem for Swift-based applications.
EnglishJEVLAB ARTThis project explores the utility of Jev as an automated evaluation framework. It demonstrates a methodology for using Jev to assess model outputs, providing a structured approach for researchers to implement comparative analysis within their own workflows.
EnglishJEVLAB ARTThis 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.
English
RaptorThis project demonstrates a dual-arm robotic system utilizing Jev as a middle-layer decision-making engine. The creator reports that inverse kinematics and physical interactions are handled through dedicated code to ensure efficient and precise operational performance.
日本語JEVLAB ARTjsort provides a utility to organize text lines based on semantic meaning. It utilizes the Jev model to perform pairwise comparisons, allowing users to sort data along a specified plain-English dimension.
EnglishJEVLAB ARTThis tool utilizes ReplyNodes web context and Vercel AI Gateway to analyze SaaS websites. It demonstrates how Jev can be applied to evaluate and provide insights on the content and structure of web-based platforms.
EnglishThis demonstration showcases a voice command interface integrated into the Autumn billing dashboard. It illustrates how spoken inputs can be used to navigate and manage financial tasks within the platform to potentially improve workflow efficiency.
English
Submit a find
한국어
Español
Français
Deutsch
繁體中文
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
610
Tools & apps
Games & real time
Start here
Agents & browsers
Research & data
Decisions & routing
Markets & experiments
Creative & growth
Devices & robotics