Submit a find
한국어
日本語
Español
Français
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
Back to the labJEVLAB / FIELD NOTES
Fresh from the lab
A dated reading list of newly added resources and JEVLAB NEWS. Come back for what changed, or follow the RSS feed in your own reader.
Remember this visit on this browser to highlight new additions next time. No sign-in or cross-device tracking.
Dates show when an item became available in JEVLAB, in UTC, not when its original source was published. Translation-only edits do not count as new resources.
36
19 Open-Source Jev Projects
This 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.
x.comSelf-Solving Rubik's Cube
This project showcases a Rubik's Cube prototype that utilizes Jev AI to perform self-solving maneuvers. The creator demonstrates an approach modeled after human problem-solving techniques instead of relying on traditional optimal mathematical algorithms.
x.comJev AI Action Label Validation
This research demonstrates how Jev AI automates quality assurance for physical AI training datasets. It showcases a method for verifying action labels at scale to improve the reliability of robotic learning models.
x.comjev.nu
This Nushell module provides an interface for the TypeSafe System One API. It enables users to execute typed decisions supported by calibrated probability outputs within the shell environment.
github.comjev-column-race
This 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.
github.comjev-phishing-bench
This repository provides a reproducible benchmark comparing Jev and Claude Haiku 4.5 across 2,000 phishing emails. It evaluates performance metrics including accuracy, calibration, latency, and cost to assess model effectiveness in detecting malicious communications.
github.comtenbin
tenbin 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.
github.commastra-jev-moderation
This project provides a streamlined moderation system for Mastra agents. It demonstrates how to handle input processing within a single file to maintain agent safety and content standards during automated interactions.
github.comtypesafe_ai Elixir SDK
This resource provides an unofficial Elixir SDK for interacting with the TypeSafe AI API. It demonstrates how developers can integrate TypeSafe AI services into Elixir applications using a dedicated client library for structured communication.
github.comtsai-civ2
This experimental project demonstrates a TypeSafe Jev agent playing the original Civilization II within a browser environment. It features a full-game harness that provides live action probabilities for the agent's decision-making process during gameplay.
github.comalmond-fastloop
This project provides a browser-based computer-use rig integrating Chrome DevTools with TypeSafe Jev. It serves as a testing environment for the Browser Use Olympics benchmark to evaluate agent performance in automated web navigation tasks.
github.comhono-jev-router
This 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.
github.comWhat is Jev Engineering?
This 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.
madewithjev.comjev-should-i-apply
This repository provides a public demonstration of Jev and TypeSafe AI integration. It illustrates how to implement decision-making logic for application processes using these frameworks, serving as a practical reference for developers exploring automated evaluation workflows.
github.combeatjev
This 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.
github.compydantic-jev-examples
This 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.
github.comtypesafe-sdk-java
This community-developed Java client provides an unofficial interface for the TypeSafe System One API. It demonstrates how developers can integrate TypeSafe services into Java-based applications using a structured client library approach.
github.comMuJoCo Robot Arm Control
This project demonstrates real-time control of a robot arm within the MuJoCo simulation environment. It utilizes a two-step decision process to manage both high-level actions and specific movement trajectories for the robotic manipulator.
x.comguard-jev
This project serves as a comment moderation playground where users can input text to observe how Jev evaluates and categorizes content. It demonstrates a practical application for automated decision-making in community management workflows.
github.compi-jev
pi-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.
github.comtypesafe-demo-mcp
This repository provides an MCP server implementation that exposes TypeSafe System One judgments, including noul, choice, and score, as functional tools for AI agents. It demonstrates how to integrate structured judgment data into agentic workflows.
github.comjev-trace-classifier
This project demonstrates the application of TypeSafe Jev noul judgment primitives to analyze the collusion.wiki corpus. It explores authorship classification by comparing human and agent-generated content using Qwen3.8-Flash-Next models in head-to-head and local configurations.
github.comJevals
Jevals provides a local testing environment designed for evaluating Jev requests. The project demonstrates how users can refine and improve their output quality by applying specific primitive operations within a controlled development workflow.
x.comAI-writing slop detector
This tool utilizes Jev to identify and flag low-quality text generated by Opus. It serves as an automated editorial assistant designed to help users filter out repetitive or unoriginal AI-generated content from their workflows.
x.comopenpoke-meets-jev
This 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.
github.comtranscript-scorecard
This project demonstrates a live support-call scoring system using TypeSafe AI and Effect. It showcases a full-stack implementation with SQLite, React, Vite, and Turborepo to manage automated transcript evaluation workflows.
github.comopenjev on Qwen 4B
This project features an MLP trained on the Qwen 4B model to provide a typesafe alternative to Jev. It demonstrates how specialized architectural training can be applied to existing language models to achieve specific functional parity.
x.comSemantic Spreadsheet Formatting
This tool demonstrates how Jev applies semantic formatting to spreadsheet data. It provides automated structural suggestions and outlines potential integration pathways for external platforms to enhance data organization workflows.
x.comCyber-Breach: The Jev Protocol
This 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.
github.comOpenCode Browser Integration with Jev
This demonstration showcases the integration of Jev with the OpenCode browser CLI. It illustrates how automated agents can perform web navigation tasks, highlighting the potential for streamlined browser-based workflows through this specific technical implementation.
x.comjev-playground
This project explores whether a System One model can effectively steer music generation. It demonstrates a workflow where Jev selects plans using enums to render sheet music, audio, and MIDI files.
github.comA city on a whale
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.
x.comtypesafe-go
This unofficial Go SDK provides a structured interface for interacting with TypeSafe AI. It demonstrates implementation patterns for handling typed responses, managing request retries, and maintaining context within Go applications.
github.comOpenJev
OpenJev 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.
github.comcitation-verifier
This 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.
github.comjev-snake
This experimental project demonstrates a Snake game implementation where the engine enforces deterministic rules. It showcases how Jev AI processes structured state data to make movement decisions during each game tick.
github.com
