JEVThe best of Jev. Real projects, practical guides and ideas from across the internet.
Updated 1 Resource
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 community post examines the gaming performance of Jev compared to Astra. It highlights the unique technical approach taken by Jev in high-speed gaming scenarios as presented by the creators.
English
x.comThis resource explores how Jev facilitates flexible, type-safe classification by treating it as a fundamental programming primitive. It demonstrates a conceptual approach to integrating classification logic directly into the development workflow for improved system reliability.
JEVLAB ARTEnglish
JEVLAB ARTjevmail is an open-source tool that uses Jev to categorize Gmail messages into specific folders like Needs reply or Spam. The creator claims it processes 1,000 emails per minute locally while maintaining read-only access to your inbox.
EnglishJEVLAB ARTThis repository provides a framework for evaluating Jev reranking performance within RAG pipelines. It allows users to measure quality, latency, and operational costs to help assess the efficiency of different reranking configurations.
English
JEVLAB ARTrouteKit is a developer tool designed for agent-native routing. It demonstrates a mechanism for selecting specific AI models based on the perceived complexity of a given task to optimize performance and resource allocation.
English
JEVLAB ARTThis repository serves as a curated directory for the Jev ecosystem. It provides a structured overview of open-source projects, facilitating discovery through plain-language descriptions and automated synchronization with GitHub metadata for community tracking.
EnglishJEVLAB ARTjev-lint is a tool that uses the Jev classifier to identify logical inconsistencies between code and its documentation. It combines ast-grep matchers with natural language queries to detect issues like misleading comments, naming mismatches, and hidden failure paths.
English
RomànThis demonstration showcases Jev processing 700 leads to predict outreach performance. The creator claims the system completes this analysis in 40 seconds, illustrating a potential workflow for rapid lead qualification and messaging optimization.
English
JEVLAB ARTThis repository provides a sandbox environment for testing the Jev model. It serves as a practical playground for developers to explore model behaviors and interactions within a structured, type-safe framework designed for experimental AI workflows.
English
JEVLAB ARTThis project demonstrates the integration of Jev to power non-player characters within a virtual representation of River Oaks, Houston. It serves as a technical experiment for implementing autonomous agent behaviors in a simulated game environment.
English
JEVLAB ARTThis tool provides an interactive workspace for exploring Jev Board datasets. It demonstrates a structured interface for querying and analyzing specific data points within the Jev ecosystem, facilitating research and data navigation for independent users.
EnglishThis command-line interface tool demonstrates an automated routing system for Jev. It accepts user tasks and subscription lists to determine which specific model or agent is best suited to process the request based on the provided input parameters.
English
Peter WangThis Chrome extension categorizes X posts to help users identify content types like engagement bait or promotional material. It demonstrates a community-developed approach to filtering social media feeds through automated content labeling.
EnglishJEVLAB ARTThis repository provides a collection of experiments using openjev, an open-source runner designed for Jev-style option-logit processing. It demonstrates how to implement and test these specific inference techniques when running local language models.
English
JEVLAB ARTThis pre-commit hook utilizes Jev to analyze staged changes against commit messages. It aims to identify potential issues such as debug code, unreferenced work, and exposed credentials before finalizing a commit.
English
JEVLAB ARTThis tool provides TypeSafe skill routing for the Hermes Agent by identifying the appropriate skill before model execution. It utilizes a standard library approach to optimize agent performance and reduce unnecessary processing costs.
EnglishThis project demonstrates a Jev-based agent navigating the ViZDoom environment. It utilizes dual decision channels, processing navigation at 5 Hz and combat actions at 12 Hz, as shown in a test run achieving 18 kills.
EnglishJEVLAB ARTThis web application demonstrates Jev playing chess against various LLMs, Stockfish, or human players. It provides a visual interface for tracking live moves, viewing Jev's move probabilities, and managing game history.
English
JEVLAB ARTThis repository evaluates whether decision models can outperform specialized rerankers. It compares TypeSafe Jev against Cohere Rerank 4, ZeroEntropy zerank-2, and a chat-model baseline across 14 datasets, providing raw API responses and bootstrap ranges for performance analysis.
English
JEVLAB ARTThis repository provides a Rust SDK designed for interacting with the TypeSafe AI API. It demonstrates how to implement client-side integration for TypeSafe services within a Rust development environment.
English
JEVLAB ARTThis tool integrates LLM planning with Jev for automated browser navigation. It provides a library, CLI, and MCP server to demonstrate how typesafe systems can manage web interactions through structured decision-making processes.
English
JEVLAB ARTThis project demonstrates an experimental model routing system for Claude Code using Jev. It aims to optimize resource usage by intelligently directing coding tasks to appropriate models at the boundary.
EnglishJEVLAB ARTAskJev provides an autonomous agent designed for website interaction. The project implements a TypeSafe System One architecture to include a safety guard that prevents irreversible user actions during automated browsing tasks.
English
JEVLAB ARTSemantic Bookmark is a Chrome extension designed to streamline browser organization. It allows users to define custom rules for automatically categorizing saved links, helping to maintain a structured and manageable collection of web bookmarks.
English
JEVLAB ARTThis Codex plugin utilizes Jev to optimize and trim excessive tool outputs. It aims to improve context management by filtering unnecessary data, helping developers maintain cleaner interaction logs within their automated workflows.
English
JEVLAB ARTThis tool utilizes Jev to analyze and classify Git commit messages and diffs. It demonstrates automated categorization of software changes, specifically identifying bug fixes, security patches, and various modification types within version control history.
English
nader dabitThis demonstration showcases Jev applied to Gmail, enabling users to perform intent-based searches. It illustrates how the system interprets natural language queries to retrieve relevant email content, highlighting potential improvements in search efficiency.
EnglishJEVLAB ARTThis repository provides a public demonstration of Jev and TypeSafe AI integration. It serves as a practical example for developers looking to implement preflight validation workflows within the Jev ecosystem.
EnglishJEVLAB ARTThis command-line tool integrates with the TypeSafe AI Jev model to perform structured analysis on text. It supports yes/no, multiple-choice, and rubric-based queries, returning calibrated probabilities for use in shell scripts, CI pipelines, and AI agent workflows.
English
JEVLAB ARTThis repository provides a curated collection of applications, libraries, and resources for the Jev and TypeSafe System One ecosystem. It serves as a central directory for developers looking to explore available tools and community-driven projects.
English
0xLogicrwThis collection catalogs the initial wave of Jev-based infrastructure, including MCP servers, routers, reviewers, and browser agents. It serves as a directory for developers exploring the current ecosystem of tools designed for Jev integration and automation.
JEVLAB ART
简体中文
Chris AdcockThis project demonstrates how Jev allows Grok Bot to directly control the Chrome browser. It aims to replace manual clicking with automated task execution, potentially increasing efficiency for browser-based workflows as claimed by the creator.
JEVLAB ARTEnglishThis 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.
English
JEVLAB ARTThis asynchronous Python client facilitates interaction with TypeSafe Jev. It enables developers to send structured queries and receive typed responses, eliminating the need for manual prose parsing in automated workflows.
EnglishJEVLAB ARTThis project demonstrates a semantic browser interface powered by Jev. It provides a framework for users to navigate web content through Jev-based agentic interactions, focusing on intent-driven browsing experiences.
English
JEVLAB ARTThis open-source platform provides a Bring-Your-Own-Key arena for evaluating Jev and other AI models. It allows users to compare output quality, operational costs, and latency metrics while identifying potential model failures.
English
Gregor ZunicThis demo by Gregor Zunic showcases a flight search implementation using Jev. It illustrates how an agent can interact with a dynamic DOM action space to navigate web interfaces and retrieve specific travel information.
English
JEVLAB ARTThis tool provides a management layer for Pi agents to ensure they complete assigned tasks. It monitors active processes and automatically restarts agents that terminate prematurely before finishing their work.
English
JEVLAB ARTST-jeved is a SillyTavern extension designed to evaluate model replies before they appear on screen. This tool allows users to implement automated filtering or analysis layers within their chat interface for more controlled creative interactions.
EnglishThis project presents a reproduction of the 151M ModernBERT model. It documents specific performance metrics including adaptive calibration error and CPU latency, while transparently detailing both successful use cases and identified failure points.
JEVLAB ARTEnglishJEVLAB ARTThis project demonstrates a minimal agent loop where Jev manages control flow while a LangChain chat model handles argument generation and final responses. It provides a structural example of integrating Jev with external language models.
English
JEVLAB ARTjevmod provides a framework for automated content moderation by applying category-specific probability thresholds. This tool allows developers to implement customizable filtering logic to manage and classify digital content effectively.
EnglishJEVLAB ARTThis project demonstrates a cost-aware LLM router designed to select the most economical model for a given query. It utilizes Jev for rapid classification, aiming to reduce operational expenses by avoiding unnecessary LLM calls.
English
JEVLAB ARTThis command-line interface tool enables users to perform calibrated judgments like ranking, rating, and triaging directly from the shell. It demonstrates an agent-ergonomic approach to interacting with TypeSafe Jev workflows for streamlined data processing.
EnglishJEVLAB ARTterrarium 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.
English
Kevin GrajedaThis project demonstrates a real-time classifier designed to assess prompt complexity. By identifying simple requests, the system enables a faster processing mode, aiming to optimize response times and improve overall user interaction efficiency within AI-driven workflows.
EnglishJEVLAB ARTDasheng is a tool that integrates speech recognition with Jev to provide real-time, word-by-word transcription of spoken audio. It demonstrates a method for live content marking and automated text capture during speech.
简体中文
JEVLAB ARTThis project provides a local MCP gateway designed for Jev tool discovery. It includes a dashboard interface to help developers manage and monitor agentic tools within their local development environment.
EnglishTypeSafe AIThis reference documentation outlines the default settings and environment variable names for the TypeSafe Python SDK. It provides developers with the specific keys required to configure API access, model selection, and timeout parameters within their applications.
JEVLAB ARTEnglishJEVLAB ARTThis project explores Jev performance through nine experiments and 28 predictions using fixed parameters. It serves as a structured research repository for analyzing specific metrics and outcomes within the Jev framework.
EnglishJEVLAB ARTThis proof-of-concept project explores Jev TypeSafe AI integration by applying it to a Game of Thrones theme. It demonstrates how structured data models can be utilized within a narrative-driven application context.
EnglishThis project demonstrates an agent designed for automated Pokémon shiny hunting. It utilizes autonomous game resets and visual checks to streamline the process of encountering rare variants within the game environment.
English
Ian NuttallThis experiment utilizes Jev to process over 3,000 social media posts. It demonstrates a method for extracting structured insights from large datasets to help creators identify and refine their content strategies through systematic questioning.
EnglishJEVLAB ARTThis project demonstrates an automated agent playing Pokemon Red using PyBoy. The system manages game logic and arithmetic while the Jev agent selects branching paths, with battle outcomes evaluated against RAM state using Brier scoring.
EnglishTypeSafe AIThis resource documents the core data structures for the TypeSafe AI Python SDK. It defines JSONValue and JSONContent type aliases to standardize how JSON-compatible data and nested mappings are handled within the library.
JEVLAB ARTEnglish
Nate HerkThis tool demonstrates real-time categorization of social media content using Jev. It automatically applies labels such as breaking, golden nugget, or slop to X posts to help users filter information streams more effectively.
EnglishTypeSafe AIThis official resource provides a collection of reference demonstrations for TypeSafe AI. It serves as a central index for users to explore practical implementations and verified examples of the platform's core capabilities and architectural patterns.
JEVLAB ARTEnglish
JEVLAB ARTwinnow is a context filtering tool for Claude Code that uses a System One model to evaluate tool outputs. It aims to improve context management by vetting information before it is processed by the primary agent.
EnglishJEVLAB ARTThis article provides a conceptual overview of Jev, clarifying its core purpose and technical boundaries. It serves as a foundational guide for developers looking to distinguish between Jev's intended functionality and common misconceptions.
日本語This 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.
English
omar ✌️This project demonstrates a system designed to capture user interface navigation sequences on demand. It utilizes Jev processing to automate the recording of UI flows, providing a tool for researchers to document and analyze interactive digital experiences.
English
JEVLAB NEWSChoi reports that AI progress is defying linear expectations, with milestones once projected for decades away being reached in mere years. This rapid advancement is driven by AI systems increasingly contributing to their own research and development cycles.
JEVLAB ART
Jozef GhermanJev Detector is a utility designed to identify low-quality text. The creator claims the tool can process approximately 10,000 words within two seconds, offering a rapid method for automated content screening and editorial assessment.
English
JEVLAB ARTThis project provides a Jev-assisted system for file retrieval and request caching. It aims to optimize workflows on Raspberry Pi devices by reducing latency through intelligent data handling.
EnglishTypeSafe AIThis official reference document outlines the core principles of System One. It serves as a foundational guide for understanding the architectural framework and conceptual design patterns utilized within the TypeSafe AI ecosystem.
JEVLAB ARTEnglishJEVLAB ARTThis project demonstrates an emoji autocomplete tool built with TypeSafe AI Jev. It showcases real-time input processing within a TanStack Start application hosted on Whop, highlighting the integration of Jev for responsive text-based suggestions.
EnglishJEVLAB ARTThis browser-based playground provides an interface for interacting with Jev, the decision model developed by TypeSafe AI. It utilizes the Vercel AI Gateway to facilitate direct experimentation with the model's decision-making capabilities within a web environment.
EnglishJev Arena is a community-driven project featuring a competitive snake game. It demonstrates Jev's operational capabilities by pitting two independent Jev instances against each other in a head-to-head battle for victory.
EnglishJEVLAB ARTThis project demonstrates semantic tool routing and typed System One decision-making for the Pi coding agent. It utilizes TypeSafe Jev to structure agentic workflows and improve the reliability of automated coding tasks.
EnglishDiogo AlmeidaDiogo 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.
EnglishJEVLAB ARTThis repository provides a framework for evaluating Jev model security. It demonstrates testing methodologies for prompt injection and vulnerable code detection, utilizing the jev-go library to conduct blind benchmarks on System One model performance.
EnglishJEVLAB ARTThis Swift 6.4 SDK provides a type-safe client for TypeSafe AI, mirroring the Python SDK 0.7.0 API. It enables structured, schema-based interactions with AI models using Swift macros for typed questions and responses.
Submit a find
한국어
Español
Français
Deutsch
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
Games & real time
Decisions & routing
36
Research & data
Agents & browsers
Tools & apps
Start here
Creative & growth
Devices & robotics