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
typesafe-image-diffusion
This project explores diffusion-style pixel art generation using a classifier. It demonstrates a method involving 256 parallel per-pixel Jev questions followed by refinement passes to construct images, showcasing an experimental approach to structured image synthesis.
github.comJev plays Tetris
This demonstration shows Jev AI playing Tetris at high speed. The creator reports the system cleared 134 lines across 357 pieces in two minutes, illustrating the model's rapid decision-making capabilities in a real-time gaming environment.
x.comGame Plan
Game Plan is a browser-based experiment designed to test how Jev processes and responds to unpredictable user inputs. It serves as a practical demonstration of input handling capabilities within the Jev ecosystem.
game-plan.adriaansendennis.workers.devtypesafe-jev-workflow
This project demonstrates an asynchronous LangGraph workflow designed to categorize inbound emails. It utilizes typed Jev choices to route communications automatically to either invoice or general processing handlers.
github.comSecond-hand Shopping Agent
This 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.
x.comCustom Jev-style models for agent workflows
This proposal explores the implementation of custom Jev-style models designed to streamline agent workflows. The author suggests that these specialized models could potentially lower computational expenses during complex decision-making tasks within automated agent systems.
x.comjev-page-verdict
This Chrome extension utilizes Jev to analyze web pages for commercial intent or firsthand reporting. It marks Google search results with existing verdicts or snippet-based estimates, while leaving low-confidence entries undecided to help users distinguish content types.
github.comjev-games
This repository provides a visual Jev laboratory environment designed for testing and interacting with various game and emulator platforms. It serves as a practical resource for developers exploring Jev-based integration within gaming software architectures.
github.comJev plays Time Crisis
This 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.
x.compi-quiet-ask
This project demonstrates the integration of TypeSafe Jev as a decision-making layer for a coding agent. It explores how structured, quiet reasoning can be applied to automate software development tasks within the pi agent framework.
github.comroverlab
roverlab is a 3D planetary rover simulation environment. It serves as a sandbox for developers to experiment with autonomous decision-making processes using TypeSafe AI frameworks within a virtual extraterrestrial terrain.
github.comjev-voice
This project demonstrates a voice-controlled macOS automation tool. It utilizes local whisper.cpp for speech recognition and integrates a single Jev TypeSafe call per command to process and execute system-level tasks on your computer.
github.comjev-auto-approve
This GitHub tool integrates Jev into your development workflow by requiring its approval before merging pull requests. It demonstrates a method for automating code review gates using Jev-based validation to ensure repository standards.
github.comPlayground
This web-based tool allows users to input state data and pose questions to receive typed responses directly in the browser. It serves as an interactive environment for testing TypeSafe AI capabilities and verifying structured output generation.
console.typesafe.aiPrimitives
This guide outlines the three core question types in TypeSafe AI: Choice, Score, and Noul. It explains the specific data structures and return values associated with each primitive to help developers structure their AI interactions effectively.
docs.typesafe.aiopen-jev by JoshuaSP
This repository explores typed JSON inference using DiffusionGemma. It provides experimental benchmark results for Every and Jev, offering a practical look at how these models handle structured data inference tasks in a research context.
github.comJev on Cloudflare AI Gateway
This 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.
x.comCookbooks
This resource provides reproducible recipes for common AI workflows, including parallel questioning, reranking, and guardrails. It demonstrates practical implementation patterns for citation checks, data extraction, and hierarchical classification to help developers build more robust and structured AI applications.
docs.typesafe.aitypesafe-triage-guard
This repository provides three composable judgment pipelines built on Jev. It demonstrates automated workflows for managing support-ticket triage, observability alert classification, and deploy-risk assessment to help streamline decision-making processes within technical environments.
github.comOCR Image Classifier
This project demonstrates an image classification workflow integrating OCR and Jev. The creator reports processing 900 images within a 40-second timeframe using this automated pipeline.
x.commobile-jev
This project provides a standalone Android agent framework where Jev handles decision-making processes. It includes a live React studio environment and demonstrates automated interaction capabilities through an Uber-themed application demo.
github.comjev-oxlint
This project demonstrates a method for integrating Jev agent skills into the Oxlint static analysis framework. It provides a technical implementation for extending linting capabilities through custom plugins designed to leverage Jev-based logic.
github.comPort Cleanup
Port 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.
github.comjcm-router
This 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.
github.comjev-harness-router
This project provides a routing mechanism for Jev tasks by evaluating model tier, required tools, skill level, and effort. It demonstrates a structured approach to task distribution within automated workflows.
github.comsiftr
siftr provides a CLI and MCP server for AI coding agents to perform semantic search and file selection. The project aims to improve agent efficiency by facilitating focused code reads and list picking within a two-second timeframe.
github.comjev-commit
This 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.
github.comJev Dogfighting Experiment
This experiment explores the integration of Jev into aerial combat simulations. The creator demonstrates ongoing development efforts to refine the AI's dogfighting maneuvers and tactical decision-making capabilities within a game environment.
x.comJanus Calibration
Janus 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.
github.comReal-time voice control for a browser
This project demonstrates using Jev to enable real-time voice commands for browser navigation. The creator claims the system processes speech into actionable browser commands within 300 milliseconds while maintaining low operational costs.
x.comUnderstanding Jev Fundamentals
This 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.
zenn.devAn audience of 100 personalities
This 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.
x.comjev-search
This 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.
github.comjev-firewall
This tool provides a real-time firewall for AI coding agents by intercepting tool calls. It uses deterministic rules and Jev-based verification to decide whether to allow, block, or request manual approval for agent actions.
github.comCorent model routing
Corent demonstrates a model routing system that utilizes Jev to evaluate prompts and quality requirements. This approach aims to dynamically select the most appropriate AI model for specific tasks before generating the final output.
x.comPractical Jev Workflows
This resource outlines six specific use cases for Jev, including fact-checking, ranking, citation verification, and agent failure analysis. It demonstrates how the tool can be applied to structured information processing and systematic quality control tasks.
x.com
