JEVThe best of Jev. Real projects, practical guides and ideas from across the internet.
Updated 4 JEVLAB NEWS posts
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 community-driven collection of over 110 AI use cases, games, and logic challenges. It features a mobile-friendly interface that allows users to edit prompts and perform A/B comparisons between different model outputs.
EnglishThis demonstration showcases Jev from TypeSafe AI engaging with the card game Balatro. The creator claims the system makes gameplay decisions within a 200-500ms timeframe, illustrating its potential for rapid interaction in complex, rule-based digital environments.
EnglishTypeSafe AIThis guide demonstrates the essential steps for integrating TypeSafe AI. It teaches developers how to configure an API key to generate structured, type-safe decisions from language models efficiently.
JEVLAB ARTEnglishJEVLAB ARTThis project demonstrates an autonomous agent designed to interact with PlayStation 2 hardware. It utilizes the TypeSafe Jev System One to process real-time visual telemetry, providing a heads-up display for monitoring the agent's performance during gameplay.
English
JEVLAB ARTThis 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.
English
John YeoThis project demonstrates how to optimize a Slack agent by utilizing Jev for improved skill and tool classification. The creator claims this implementation results in significantly faster response times for automated tasks.
English
JEVLAB ARTThis project provides a MoonBit client for Jev and demonstrates a gomoku match between two Jev instances. It includes timing logs to track the performance of the automated gameplay sessions.
English
JEVLAB ARTThis project demonstrates a semantic routing mechanism for the Hono web framework. It utilizes Jev to interpret and route incoming HTTP requests based on their underlying meaning rather than traditional path-based patterns.
English
JEVLAB ARTjevmlx enables parallel constrained decision-making for MLX models running on Apple Silicon. This tool facilitates the generation of typed, schema-valid JSON outputs within a single forward pass, streamlining structured data extraction from local machine learning models.
EnglishJEVLAB ARTThis browser-based game challenges users to compete against Jev in identifying spam messages. It serves as an interactive demonstration of Jev's classification capabilities in a simulated real-world filtering scenario.
English
t0t0This project demonstrates a Jev-based system that monitors 25 WhatsApp customer groups simultaneously. It uses an automated filtering process to trigger an LLM only when urgent issues are detected, aiming to streamline customer support workflows.
JEVLAB ART
Español
JEVLAB ARTpi-heed provides runtime constraints for the pi coding agent. It demonstrates a safety mechanism that verifies side-effecting tool calls against user intent before execution, utilizing TypeSafe Jev to enhance operational control during automated coding tasks.
English
JEVLAB ARTThis project demonstrates an automated trading implementation using Jev on the Kuru MON-USDC market. It executes a single trading decision for every Monad blockchain block, showcasing how Jev agents can interact with decentralized exchange liquidity.
EnglishJEVLAB ARTThis project demonstrates a Typesafe.ai System One model designed to navigate Neo4j graph databases. It utilizes a classifier to analyze neighboring relationships, providing a structured approach for Jev-based graph traversal and decision-making processes.
English
Faadil ShaikThis experiment demonstrates Jev controlling Super Mario Bros. through fast inference and structured outputs. It serves as a technical showcase for how AI models can potentially manage real-time interactive gaming environments.
English
KaiThis project demonstrates using Jev to automate the crawling of job listings from company websites. The creator claims this approach offers faster data retrieval compared to traditional LLM-based methods for monitoring career pages.
EnglishThis project demonstrates an LLM-based pipeline designed to automate the classification of tax documents. It illustrates a workflow for organizing financial paperwork, though users should independently verify the accuracy and reliability of the automated categorization results for their specific tax needs.
EnglishJEVLAB ARTThis repository provides an idiomatic Go SDK designed for interacting with the TypeSafe AI API. It serves as a developer tool to facilitate integration and communication with the service using standard Go programming patterns.
English
JEVLAB ARTThis enhancement pack provides TUI scrollbar and context-meter patches for MiniMax Code CLI. It integrates Jev Ultrafast and Playwright MCP for browser tasks while including compaction repairs for local vLLM environments on arm64 hardware.
EnglishJEVLAB ARTtoolgate provides a calibrated tool-call firewall for AI agents, utilizing TypeSafe Jev to manage automated interactions. It functions as a hook for Claude Code, aiming to enhance security by regulating how agents execute external tools.
EnglishJEVLAB ARTThis project features a 1v1 quickscope arena game built using Three.js and the TypeSafe System One framework. It demonstrates real-time competitive mechanics within a browser-based environment for Jev-based development.
English
JEVLAB ARTThis tool provides a per-prompt capability router for coding agents. It resolves installed skills, MCP servers, and commands using TypeSafe Jev while attempting to measure the effectiveness of these injections on agent performance.
English
JEVLAB ARTThis project provides a decision layer for coding agents that enforces deterministic rules before model calls. It integrates as a Claude Code hook, MCP server, and policy engine to manage agent behavior through structured Jev requests.
English
Joao BortottiThis project demonstrates the use of Jev to manage real-time 3D character expressions. It showcases how automated decision-making processes can influence digital animation behavior dynamically during live interactions.
EnglishJEVLAB ARTThis project implements a two-stage matching system designed to connect user goals with the Model Context Protocol catalog. It demonstrates how TypeSafe Jev can be utilized to streamline agent-based tool discovery and selection processes.
EnglishThis open-source tool provides a mechanism for calibrating confidence thresholds within Jev systems. It demonstrates a practical approach for users to adjust sensitivity settings to better align model outputs with specific operational requirements.
English
x.comThis collection highlights various practical Jev projects, including browser-based agents and automated trading bots. It serves as a resource for developers looking to explore functional implementations and real-world applications within the Jev ecosystem.
JEVLAB ART
日本語
JEVLAB ARTThis tool utilizes Jev to scan codebases for deceptive or data-stealing patterns. It aims to identify suspicious files and specific line ranges, allowing developers to review potential security risks before executing the code.
English
JEVLAB ARTjev-hub serves as a curated directory aggregating long-form articles and demonstration videos regarding Jev, the TypeSafe AI System 1 model. It provides a centralized resource for exploring community-led discussions and visual examples of the framework in action.
EnglishJEVLAB ARTinvalidate provides an invalidation layer for AI memory systems built on TypeSafe Jev. It implements a lease-based mechanism where stored facts are automatically retired when new, conflicting evidence is introduced.
English
toksThis experiment demonstrates using Jev alongside an LLM to play Doom. It explores the capability of simulating multiple potential future outcomes simultaneously during gameplay to inform decision-making processes within the game environment.
English
Max BladeThis demonstration showcases Jev managing multiple instances of Subway Surfers simultaneously. The creator claims the system achieves high-speed gameplay across 50 concurrent sessions for a low cost, though these performance metrics remain unverified by independent testing.
English
JEVLAB ARTThis local proxy utilizes TypeSafe Jev to dynamically route subagent requests to specific Claude models and effort levels. It is designed to manage specialized tasks independently while preserving the state of your primary chat session.
EnglishThis 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.
EnglishJEVLAB ARTThis Chrome extension integrates Jev into X.com, allowing users to analyze social media posts directly within their browser. It demonstrates a practical application of Jev for real-time content evaluation while browsing the platform.
EnglishThis 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.
EnglishJEVLAB ARTThis plugin integrates Jev with AI agents like Claude Code to handle non-text output steps. It demonstrates a workflow for typed escalation back to the LLM, with the creator reporting p50 latency of 230ms and costs around $0.02 per 1,000 judgments.
EnglishThis project demonstrates a predictive app launcher that utilizes Jev to interpret user intent. It aims to streamline application discovery by anticipating user needs through intent-based processing.
English
JEVLAB ARTThis project demonstrates a method for filtering AI assistant memories using Jev. It focuses on retrieving information based on relevance rather than simple resemblance to improve the accuracy of context-aware interactions.
English
Chris TateThis community tool enables Jev to execute decision-making processes directly through command-line interfaces. It is designed to assist developers in managing agent system logic within terminal-based workflows.
JEVLAB ARTEnglishJEVLAB ARTThis repository provides an exploratory look at Jev, featuring a collection of live demonstrations and runnable code snippets. It serves as a practical resource for auditing claims and understanding the core mechanics of TypeSafe AI implementations.
English
JEVLAB ARTThis guide provides developers with a technical overview of implementing the Jev System One model. It outlines practical integration steps and usage patterns for leveraging TypeSafe's architecture in software development workflows.
English
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.
EnglishJEVLAB ARTThis project provides a collection of interactive graphical modules including routing, a Tetris implementation, swarm simulations, and a gauntlet challenge. It serves as a practical demonstration of Jev-based application development and game logic implementation.
English
Marek SotakThis tool monitors user interactions to identify signs of confusion or difficulty. It utilizes Jev to determine and provide contextually appropriate interventions, aiming to assist users only when they encounter challenges during their workflow.
English
Eugene CheahSimple Jev is an open-source library designed to convert Hugging Face models into Jev-style endpoints. This tool aims to improve accessibility by simplifying the integration process for developers looking to deploy machine learning models within the Jev ecosystem.
EnglishJEVLAB ARTJevLint 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.
EnglishJEVLAB ARTThis unofficial Rust client provides a type-safe interface for interacting with System One TypeSafe AI. It demonstrates a fluid API for constructing requests and handling typed responses, including token usage and cost estimation.
EnglishJEVLAB ARTThis research project investigates how the Jev architecture handles Spanish language processing. It serves as an experimental audit to evaluate linguistic performance and character handling within the Jev framework.
English
JEVLAB ARTThis repository provides an unofficial Chinese translation of the official Jev documentation by TypeSafe AI. It covers core System One concepts, primitives like Choice, Score, and Noul, and includes a static site generator for local deployment and offline reading.
JEVLAB ARTThis tool enables offline search within Obsidian vaults. It features an optional Jev reranking mechanism for search results, which requires explicit user authorization before processing to ensure control over how information is prioritized.
EnglishTypeSafe AIThis TypeSafe AI reference guide outlines essential strategies for implementing guardrails in large language models. It demonstrates how to establish safety boundaries to manage model outputs and mitigate potential risks during deployment.
JEVLAB ARTEnglishJEVLAB ARTThis experiment compares Jev against Mistral and Gemini models for validating local event data. It examines performance metrics regarding latency and operational costs when processing structured event listings.
English
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.
EnglishJEVLAB ARTThis project presents a Rubik's Cube puzzle interface designed to test Jev-based logic. It serves as an interactive demonstration of how the model handles spatial reasoning and sequential problem-solving tasks within a game environment.
EnglishJEVLAB ARTThis project demonstrates the use of the RLCD-type Jev model from TypeSafe AI to evaluate agentic coding sessions. The creator claims this approach provides an independent and cost-effective method for assessing automated programming tasks.
EnglishThis project demonstrates a real-time overlay for League of Legends that utilizes Jev to analyze active game states. The creator claims the tool provides live win-probability predictions based on current match data.
EnglishJEVLAB ARTjev-test-filter uses Jev to analyze git diffs and identify which tests are affected by code changes. It automatically generates and executes the necessary filter arguments for test runners like vitest, Playwright, cargo test, and go test.
JEVLAB ARTThis resource introduces the TypeSafe Jev system, a new class of decision-only models. It provides a technical roundup covering the API, evaluation frameworks, adapter implementation, and skill integration for developers working with these specialized architectures.
EnglishLeonardo Bissoli demonstrates how Jev facilitates structured AI decision-making. The presentation covers the integration of confidence scores, operational boundaries, and practical examples for implementing these decision frameworks within software applications.
PortuguêsJEVLAB ARTThis project provides a utility to transform open-source language models into functional classifier or Jev endpoints. It demonstrates a streamlined approach for developers to implement decision-making capabilities using existing model architectures without requiring complex infrastructure.
English
JEVLAB ARTjevify is an agent skill designed to identify TypeSafe Jev opportunities. It assists users in crafting structured, typed questions and incorporates insights derived from recent community experiments to improve overall interaction quality.
English
x.comThis community tutorial explores Jev capabilities, featuring practical demonstrations of browser automation and AI memory management. It provides a foundational look at how these agents interact with web environments and retain contextual information for tasks.
English
JEVLAB ARTThis repository provides a curated collection of Jev projects, SDKs, and resources. It serves as a central directory for developers exploring TypeSafe AI's System One model, which focuses on typed decision-making using Choice, Score, and Noul frameworks.
English
Sim AudienceThis experiment showcases the use of Jev to conduct A/B testing across 4,000 distinct demographic personas. It demonstrates how the platform processes and evaluates content performance across a large, simulated audience base to provide comparative insights.
EnglishJEVLAB ARTThis repository provides a curated overview of various Jev-based applications. It explains their core functionality, underlying principles, and comparative pros and cons to help users understand how these tools operate in practical scenarios.
EnglishJEVLAB ARTLitJev is a reproduction of the Jev framework that enables Qwen models to function as decision-making engines. It implements the /v1/systemone schema to output choices and scores without requiring model training or generating additional text.
EnglishJEVLAB ARTThis MCP server maintains a per-project ledger that tracks session history. It utilizes the Jev evaluation model via Vercel AI Gateway to recall past task context, allowing current sessions to build upon previous work.
EnglishJEVLAB ARTThis tool analyzes WeChat conversation threads to evaluate emotional tone, user intent, and reply quality. It provides a technical approach to interpreting social interactions within messaging platforms by processing text data for sentiment and communication patterns.
English
amitThis project demonstrates a multi-agent simulation where 100 distinct personalities respond to user input. It showcases how Jev can be utilized to manage complex, individual interactions within a large-scale synthetic audience environment.
EnglishJEVLAB ARTThis experimental plugin explores Jev-assisted model routing by incorporating budget and capability constraints. It serves as a technical experiment for managing model selection processes, though API access remains pending for full implementation.
EnglishJEVLAB ARTJev Gamecast is a React-based application designed for sports enthusiasts. It demonstrates a replay-first architecture that allows users to query live sports data using Jev-typed questions to retrieve specific game insights and historical match information.
English
Submit a find
한국어
Français
Deutsch
简体中文
繁體中文
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
3
Games & real time
Start here
Agents & browsers
Research & data
Markets & experiments
Decisions & routing
Creative & growth
Tools & apps
