Jev Semantic Find
A Chrome-extension demonstration uses Jev for intent-based find on a page.
From musical experiments to everyday automation. Discover an idea, watch it work, and make something of your own. Explore projects that call Jev in realtime or nearly.
A Chrome-extension demonstration uses Jev for intent-based find on a page.
A creator-posted Minecraft speedrun pairs Jev movement decisions with asynchronous Astra planning on a specified seed.
A creator demonstrates article and job searches with a Jev browser skill in Antigravity CLI and Codex.
A Drape experiment uses Jev decisions to drive a virtual outfit-selection interface.
An open-source CLI helps developers tune Jev criteria using good and bad examples.
A creator reports using Jev in a client-site audit workflow; claimed savings and output quality have not been independently reproduced.
A creator-posted accounting prototype connects the Jev API to a mock interface.
A Jev toolkit for agent model routing, memory filtering, compaction, skill selection, triage, and bounded computer/browser decisions.
An experiment combines json-render with Jev for responsive generated interfaces.
A Box demonstration uses Jev decisions to organize incident reports into escalation, monitoring and review folders.
A creator demonstrates a Jev tax-document classifier. Reported accuracy, speed and costs apply to the creator’s corpus and are not independently validated.
An open benchmark pairs Jev tool selection with Mercury-generated arguments.
Shipper presents a Jev-assisted workflow for turning website URLs into mobile applications; the full build path is not independently reproduced.
Video unavailable. Open the source below.
A macOS demo organizes downloads according to natural-language rules.
Video unavailable. Open the source below.
A creator compares a Jev-assisted calendar workflow with Codex computer use; the claimed speedup has not been independently measured.
Video unavailable. Open the source below.
A Japanese-language demo sorts live comments into useful groups.
A creator-posted gameplay demo presents Jev controlling four Smash characters; the underlying harness is not independently verified.
A Minecraft agent pairs Jev reactions with GPT-6 Astra planning.
Video unavailable. Open the source below.
A presentation demo changes slides as its presenter speaks.
An OpenCode plugin demonstration uses Jev to assess the intent of commands against an allowed-domain policy.
Video unavailable. Open the source below.
A Claude Code plugin experiments with pruning context instead of summarizing it.
A decision layer for agent ranking, verification and action assessment.
A continuous livestream lets Jev attempt to defeat Minecraft's Ender Dragon one decision at a time.
Video unavailable. Open the source below.
A demo assistant connects search, reference, weather and personal tools.
Video unavailable. Open the source below.
An experiment reconstructs a piano sequence by repeatedly choosing keys.
A creator demonstration applies Jev to a collection of live ads for structured marketing analysis.
A Chrome extension lets agents browse and act in the current page with Jev decisions.
A Mac pointer experiment uses local OmniParser/CoreML detection and sends text labels to Jev to choose the next click.
A remote-browser loop combines Jev action decisions with Stagehand execution.
A gameplay prototype uses Jev to automate Minecraft for extended sessions at low token cost.
A local web app classifies exported Telegram posts and conversations by intent, quality, sentiment, topic, and tone.
A CLI recommends an agent or model from a task and the user's available AI subscriptions.
A demonstration classifies a 100-email test set with Jev, then asks a larger model to handle uncertain results.
A classifier produces small pixel-art images through repeated color choices.
A voice prototype uses Jev to decide whether a speaker has finished and how long to keep listening.
A PostgreSQL extension exposes Jev categorical classification inside SQL.
A PR-review demonstration turns Jev probabilities into review routes, with uncertain critical checks handed to a human or larger model.
A voice-browser demo combines speech input and Jev-selected actions in a rapid interaction loop.
A creator tests Jev in a memory workflow and reports lower token use and faster retrieval; the measurements remain creator-reported.
Skillbox uses Jev to return relevant agent skills directly from a query.
A browser extension removes ads, cookie banners and other page clutter with reusable Jev rules.
Turn questions about household state into sensors and automation inputs.
Video unavailable. Open the source below.
An Android agent navigates apps with a live studio and execution trace.
Video unavailable. Open the source below.
A browser extension hides posts that match a user’s natural-language rules.
A music playground that turns a chosen style into sheet music, playback and MIDI.
A command-line tool classifies Git commits by change type, bug fixes and security relevance.
A cube-solving experiment lets Jev choose cases while deterministic code checks each move.
Video unavailable. Open the source below.
An experimental market-analysis demo combines price forecasts with Jev decisions.
A Rust CLI ranks installed agent skills against live session context with Jev, then applies abstention and local feedback around the typed result.
A prototype uses Jev to simulate responses from fictional product personas. These are model outputs, not customer research.
A Discord bot uses Jev to filter spam and scam links and escalate repeat offenses.
An MCP tool supplies repeated software-quality measurements to coding agents.
A router uses Jev to choose the model that best fits each incoming request.
A personal-assistant agent uses Jev to select one tool from a 100-tool catalog before each model step.
A simulated RISC-V CPU uses Boolean lookup tables supplied by Jev.
Natural-language requests select and configure real UI components.
An experimental writing interface uses Jev to analyze posts while they are being drafted; predictive quality is unverified.
Video unavailable. Open the source below.
A browser agent selects actions from the current DOM and demonstrates flight search.
An experiment builds text-like output by asking Jev to choose from a few hundred words and punctuation marks.
A DuckDB extension classifies rows in CSV, Parquet, and DuckDB tables with Jev.
Video unavailable. Open the source below.
A trading experiment connects rapid decisions to an on-chain order book.
A Minecraft bot gathers materials and builds a supplied Canadian flag blueprint.
A staged code-review workflow follows Jev signals through focused checks and a local dashboard.
A ViZDoom test uses separate Jev decision channels for navigation and combat.
A local router chooses a model tier for each Claude Code or Codex turn.
Video unavailable. Open the source below.
A browser-use preview pairs Jev decisions with OpenCode's browser-use CLI for fast interaction loops.
A small app-testing demo uses Jev with OpenCode for a fast browser interaction loop.
A macOS computer-use loop uses OCR and Jev to choose bounded actions.
Video unavailable. Open the source below.
A prototype uses Jev as a codebase classifier; the creator frames it as an experiment in reducing overengineering.
The Loki agent offers Jev as an optional typed-decision companion and session model router.
A repository governance kernel can attach optional Jev trajectory observations to its assurance loop while retaining deterministic policy, interlocks and proof rules.
A terminal tool exposes typed Boolean, Choice and Score evaluations with Jev as the default evaluation model.
A terminal coding agent uses Jev for typed turn, risk and progress judgments before its generative planning and tool loop.
No projects match these filters.