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.
JEVLAB ARTThis repository provides a curated collection of public projects, integrations, and community discussions centered on Jev. It serves as a central directory for developers exploring TypeSafe AI's System One model for implementing typed decision-making architectures.
English
JEVLAB ARTtenbin provides an MCP server and agent skill for the TypeSafe AI System One API. It demonstrates how to decompose judgments into choice, score, and noul questions, perform linting, and calibrate thresholds using labeled data.
English
JEVLAB ARTlkclean is a Chrome extension that filters LinkedIn feeds by using Jev to classify posts. It collapses engagement bait and irrelevant content while providing transparent explanations for every decision made by the model.
English
JEVLAB ARTpi-jev is an extension suite designed to enhance Pi interactions using Jev. It demonstrates methods for selective context compaction and automated model routing to help manage information flow and optimize processing within the agent environment.
English
JEVLAB ARTjevlogs provides an open-source utility for triaging OpenTelemetry logs. The project demonstrates a method for scoring log signals to prioritize data before performing resource-intensive LLM analysis, aiming to optimize processing efficiency for observability workflows.
English
JEVLAB ARTriff is a lightweight prose linter that applies ruff-style rule codes to writing. It utilizes the TypeSafe Jev model to provide automated stylistic feedback and consistency checks for technical documentation and general text.
English
JEVLAB ARTjgrep is a command-line utility that filters text based on semantic descriptions rather than literal patterns. It utilizes the Jev decision model to interpret line meanings, with the creator reporting processing speeds of approximately 200 milliseconds per line.
EnglishThis demonstration showcases a MakerMods robot arm operating within the MuJoCo simulation environment. It illustrates how the system processes JSON-formatted state inputs and action selections to control robotic movement in a virtual space.
English
Higgsfield AI 🧩This demo showcases how Jev dynamically selects the most appropriate AI models for specific video and image generation tasks within the Higgsfield platform. It illustrates an automated approach to optimizing model selection for creative workflows.
EnglishJEVLAB ARTJanus demonstrates a calibration and confidence-based routing system for decision-making tasks. The project reports an 80.2% accuracy rate on the Banking77 dataset, with the author claiming a specific cost efficiency of $0.103 per 500 decisions.
EnglishTypeSafe AIThis official TypeSafe AI reference explains the mechanics of function calling. It demonstrates how to integrate external tools and structured data processing into LLM workflows to improve task execution and enable dynamic interaction with external systems.
JEVLAB ARTEnglishJEVLAB ARTThis repository demonstrates a Jev-style calibrated decision model built on the Qwen3.5-0.8B architecture. It explores the implementation of Choice, Score, and Noul decision frameworks within a compact language model environment.
EnglishThis community-driven project utilizes Jev to analyze and refine combat techniques. It serves as a digital training assistant for players looking to improve their performance through systematic feedback on fighting mechanics.
English
JEVLAB ARTThis library provides an idiomatic Elixir client for interacting with the TypeSafe AI API. It enables developers to integrate TypeSafe AI services into their Elixir applications using native language patterns and structures.
EnglishTypeSafe AIThis official TypeSafe AI reference guide demonstrates how to implement line-by-line semantic search functionality. It provides developers with the necessary patterns to perform precise text retrieval within structured datasets.
JEVLAB ARTEnglish
x.comThis resource introduces Jev as an AI-native system designed for decision-making. It demonstrates how the framework moves beyond simple text generation by defining potential outcomes and programmatically selecting the most appropriate path for autonomous operations.
JEVLAB ARTEnglishJEVLAB ARTThis repository provides a collection of Jev-powered tools for Hermes agents. It demonstrates implementations for model routing, memory management, data compaction, skill selection, and automated computer or browser interaction capabilities.
English
0xCodilaThis project demonstrates a routing configuration for Grok Bot using Jev. The creator claims this seven-step setup optimizes AI agent task management to potentially lower operational costs and improve execution speed.
EnglishThis demonstration showcases an SEO audit process using Jev to analyze website internal link structures. The creator claims the tool completes the audit in 45 seconds, providing a rapid method for identifying site architecture improvements.
English
JEVLAB ARTThis repository provides a collection of concise, single-file demonstrations showing how to integrate Pydantic AI with Jev. These examples serve as practical references for developers looking to implement type-safe AI workflows using these specific tools.
English
Alan DaitchThis 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.
EspañolJEVLAB ARTJevForge provides an end-to-end stack for auditable data construction using Jev-style structured decision-making. The project demonstrates local model serving, interactive replay, and evaluation tools for Qwen3.5-0.8B training workflows.
EnglishVibecheck explores methods for managing humor and tone within social platform interactions. This project demonstrates how automated systems can be applied to community moderation and content curation to maintain specific engagement standards.
EnglishJEVLAB ARTThis tool demonstrates a recursive approach to managing Jev choices within a taxonomy. It enables users to navigate more than 255 options while maintaining compatibility with TypeSafe Jev's established choice limitations.
EnglishJEVLAB ARTJev Auto Router demonstrates a per-call routing system for Codex that dynamically selects GPT models and effort levels. It utilizes a local proxy to maintain tool loops while employing independent verification to confirm task completion.
EnglishJEVLAB ARTThis project provides a Rust implementation of the system-one-adapter, designed to facilitate LLM-backed evaluations. It serves as a technical port for developers looking to integrate system_one evaluation methodologies within a memory-safe Rust environment.
English
Everton CarneiroThis tool assists developers in optimizing App Store visibility by analyzing competitor keyword strategies. It utilizes Jev to filter and identify relevant search terms, helping users refine their metadata for better discoverability within the marketplace.
English
JEVLAB ARTThis repository provides an evidence-based map of Jev performance, utilizing actual API-call receipts to document operational successes and failures. It serves as a practical resource for understanding system reliability through empirical data rather than leaderboard rankings.
English
Marc KöhlbruggeThis project demonstrates a real-time assistant using Jev and local Whisper to process voice commands. It classifies user actions and interacts with the screen via a Swift application designed to enhance accessibility through automated input handling.
JEVLAB ARTEnglish
JEVLAB ARTjevsql integrates natural-language predicates into SQL queries using TypeSafe Jev. This tool enables users to filter, rank, and classify database rows based on semantic meaning while incorporating batching, caching, and cost-management features for query execution.
English
JEVLAB ARTThis guide demonstrates how to integrate Jev into LangChain workflows to route requests between different models. It specifically focuses on implementing safety measures to identify and block potentially risky tool calls during execution.
English
JEVLAB ARTThis modification for Claude Code integrates the Jev model to assist with agent decision-making. It demonstrates how to dynamically rank installed skills based on specific prompts and provides automated responses to internal agent queries when confidence thresholds are met.
English
JEVLAB ARTThis project demonstrates Jev's capability to play chess by executing moves within a benchmark environment. The creator claims the implementation achieves high-quality gameplay while maintaining low computational costs for the underlying model.
EnglishThis video demonstrates Jev as a classification model through various practical examples. It showcases how the system handles categorization tasks, though viewers should note these are creator-led demonstrations rather than independent performance benchmarks.
English
Rob HallamSuperX 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.
English
JEVLAB ARTThis playground provides an interactive environment for building Jev structures including Choice, Score, and Noul components. It allows users to visualize live probability distributions and test TypeSafe Jev configurations directly within a web-based interface.
EnglishJEVLAB ARTThis repository provides a plugin designed to integrate Claude Code functionality with the jev ecosystem. It serves as a utility for developers looking to extend their agentic workflows using specific Claude-based code automation tools within the jev environment.
EnglishJEVLAB ARTThis project demonstrates a workflow for verifying academic citations. It utilizes Claude to extract supporting quotes and Jev to score the alignment between citations and their source material, ultimately requiring human oversight to confirm the accuracy of the claims.
English
Marcel Pociot 🧪This macOS utility demonstrates an automated system for managing files within the Downloads folder. It allows users to define custom rules to categorize and move incoming documents into specific directories based on file type or other attributes.
EnglishJEVLAB ARTThis WordPress plugin integrates the TypeSafe System One API, enabling developers to query content for structured data like probabilities, categories, and scores. It leverages the WordPress Connectors API for secure key management without using generative text features.
JEVLAB ARTnotra is a marketing analytics platform that demonstrates how to route brand-visibility classification tasks away from LLMs and toward Jev boolean logic. This approach aims to replace probabilistic model outputs with deterministic decision-making processes.
English
JEVLAB ARTjev-router is a tool designed to optimize costs within claude code by dynamically routing tasks to the most economical model available. It aims to streamline development workflows by automating model selection based on task requirements.
EnglishThis resource showcases an implementation of computer use built on Jev. The creator claims significant performance improvements over Opus 5, noting increased speed and cost-efficiency, while highlighting the system's ability to generalize across different operating systems.
EnglishJEVLAB ARTevals.typesafe.aiTypeSafe AIThis resource outlines the methodology used to evaluate System One workflows. It provides comparative performance data across various models, offering a structured approach for assessing AI workflow reliability and output quality in practical applications.
English
JEVLAB ARTThis repository provides a framework for implementing bounded, TypeSafe Jev workflows specifically designed for coding agents. It demonstrates how to structure agentic processes to maintain reliability and safety within automated software development tasks.
EnglishJEVLAB ARTagent-chaperone provides a security layer for AI agents by intercepting and screening tool calls and results. This MCP proxy and hooks adapter allows developers to inspect interactions before they are processed by the agent or the external tool.
English
JEVLAB ARTqualm provides a framework for typed decision-making in System One models. It enforces compile-time safety by distinguishing between confident and uncertain model outputs, requiring developers to explicitly handle both states within their application logic.
EnglishTypeSafe AIThis interface defines the request body for the SystemOne API endpoint. It specifies the required structure for model overrides, question sets, and state data, ensuring consistent communication when interacting with the TypeSafe AI system.
JEVLAB ARTEnglishTypeSafe AIThis official documentation provides a foundational overview of the TypeSafe ecosystem. It serves as the primary entry point for understanding core concepts and architectural principles governing the platform's approach to safe and reliable AI integration.
JEVLAB ARTEnglishThis integration demonstrates how Jev connects with Cal.com to identify available time slots across team calendars. It aims to streamline the meeting coordination process by automating the search for scheduling overlaps.
EnglishJEVLAB ARTThis tool enables developers to select specific Git changes for staging by providing plain-language descriptions. It demonstrates a workflow for automating version control interactions through natural language processing.
Englishdocs.typesafe.aiThis resource outlines the technical specifications, pricing, and API usage for the Jev 1.13 model. It explains how to utilize the state-based architecture for domain-specific tasks without fine-tuning.
JEVLAB ARTJEVLAB ARTThis unofficial PHP SDK provides an interface for the TypeSafe AI System One API. The creator claims it maintains functional parity with official JavaScript and Python SDKs, though it is not affiliated with TypeSafe AI.
English
JEVLAB ARTThis project features a non-autoregressive decision engine built on ModernBERT. It demonstrates the integration of calibrated uncertainty via RLCD and provides a WebGPU-based playground for auditing TypeSafe AI Jev benchmarks.
EnglishJEVLAB ARTThis project demonstrates the integration of Jev for browser automation tasks. It provides a framework for agents to perform web navigation and execute decision-making processes based on the provided Jev logic.
English
x.comThis integration demonstrates how Jev utilizes Cloudflare AI Gateway to deliver structured responses to user queries. It highlights the technical implementation of structured data processing within the Cloudflare ecosystem for improved query handling.
JEVLAB ARTEnglishJEVLAB ARTThis repository provides a static dashboard comparing Jev, luna-none, and luna-low models on Japan's 2026 Common Test. It serves as an experimental benchmark to evaluate how these specific AI architectures perform on standardized academic examination questions.
English
iagolastThis community project demonstrates how Jev can be utilized to automatically categorize company invoices for accounting purposes. The creator showcases a workflow designed to streamline financial data entry and organization tasks.
JEVLAB ARTEspañolMakerMap is a discovery tool that utilizes Jev technology to connect users with local makers. The creator claims the platform provides high-accuracy matching for community-based artisan searches, though these performance claims remain independent of verified third-party benchmarks.
EnglishJEVLAB ARTcommentcop is a Jev-powered utility designed to evaluate and audit source code comments. It provides an automated mechanism to review documentation quality, helping developers maintain clearer and more effective code annotations within their projects.
EnglishJEVLAB ARTThis project provides a Spring Boot starter for integrating TypeSafe Jev. It demonstrates how to utilize Spring MVC and RestClient to streamline Jev implementation within standard Java-based web application architectures.
EnglishJEVLAB ARTOpenJev provides a Jev-inspired decision API utilizing TypeSafe.ai concepts. This project features choice, score, and noul primitives alongside local mock servers and SDKs for Python and TypeScript, serving as a framework for developers to experiment with decision-making logic.
EnglishThis prototype demonstrates a system designed to classify patient symptoms and update diagnostic information in real-time. It utilizes medical ontologies to process live clinical transcripts, aiming to assist practitioners during consultations.
EnglishThis community experiment compares the performance of Jev against GLM 5.3 in a chess game. The creator claims the test highlights differences in processing speed and cost efficiency between the two models.
EnglishJEVLAB ARTThis Minecraft modification introduces a gameplay challenge where Jev attempts to complete the game from scratch. The project demonstrates an unscripted approach to speedrunning, focusing on organic progression rather than following a pre-determined route.
EnglishTypeSafe AIThis TypeSafe AI reference explains the speculative fan-out pattern. It demonstrates how to improve system responsiveness by initiating multiple concurrent requests and selecting the first successful result to reduce overall latency in AI-driven workflows.
JEVLAB ARTEnglish
JEVLAB ARTThis experiment demonstrates a Gomoku match between two Jev instances. It provides source code and timing logs to illustrate how Jev agents interact and process game state during competitive play.
日本語
JEVLAB ARTThis laboratory project demonstrates multi-drone autonomy using TypeSafe Jev reflex decision-making. It explores how these reflex actions can be integrated with optional System 2 strategy guidance to manage complex aerial navigation tasks.
EnglishJEVLAB ARTThis plugin integrates with Claude Code and other tools to select AI models based on Jev decision logic and OpenRouter pricing. It aims to balance intelligence, speed, and cost for specific tasks.
English
JEVLAB ARTThis project provides an open-source alternative to Jev, enabling typed and calibrated decision-making using open-weights LLMs. It demonstrates how to achieve these outputs within a single forward pass using Hugging Face and vLLM integration.
EnglishJEVLAB ARTThis repository provides an independent analysis of Jev 1.13.0. It documents controlled prompt experiments and raw data to help users verify model behavior and performance characteristics through offline testing.
EnglishJEVLAB ARTThis project provides a Rust-based client implementation for interacting with the TypeSafe System One API. It serves as a foundational tool for developers looking to integrate Jev functionality directly into their Rust applications.
English
Submit a find
한국어
Français
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
880
Tools & apps
Decisions & routing
Agents & browsers
Devices & robotics
Start here
Research & data
Games & real time
Markets & experiments
