Jev Ultrafast
A browser loop where Jev selects an operation and page element, with a text model handling field input.
Search by the job you want to do, a tool name, or your preferred language.
Public projects, checked against their original sources.
A browser loop where Jev selects an operation and page element, with a text model handling field input.
An Android agent using Jev decisions and Mobilerun, with a live studio, CLI, and execution traces.
Add sentence-by-sentence Jev judgment meters to a video.
Let Jev choose NES controller actions from structured emulator state.
Classify Git history by bug fixes, security changes, and change type.
Watch Jev choose a trading side from a live Monad order book.
A macOS control loop that combines OCR and accessibility data with Jev action selection.
Turn Jev answers about household state into Home Assistant sensors and automation responses.
Play a browser arena match against a Jev-driven opponent.
A staged Jev workflow for inspecting Git changes or source files, with a local review dashboard.
A Go CLI and MCP server that lets coding agents request typed Jev evaluations.
The official JavaScript and TypeScript client, with answer types inferred from your questions.
Use Jev through the AI SDK evaluation API, with Choice, Score, and Boolean questions in one request.
Official synchronous and asynchronous Python clients for Choice, Score, and Noul questions.
An official agent skill for designing TypeSafe workflows and finding the relevant API guidance.
A community Rust client with async and blocking APIs, typed answers, and configurable retries.
An independent Go SDK with question constructors, typed answer accessors, and context support.
A CLI and MCP browser tool pairing Jev decisions with agent-browser actions.
A Playwright browser harness splitting goal planning, typed action decisions, and text generation.
A Pi extension that adds Jev assessments before tool use and after file changes.
Explore a Neo4j graph by asking Jev which relationship to follow and whether the goal is reached.
A RubyLLM 2 provider that expresses Jev questions through RubyLLM's structured output interface.
A community n8n node for adding typed Jev questions to automation workflows.
An agent-loop experiment where Jev chooses actions and a LangChain model supplies text.
Small Pydantic AI examples that use Jev at prompt, tool, and application decision points.
Run System One-shaped evaluations through other model APIs to build comparisons with Jev.
A Discord bot that evaluates spam and scam signals with Jev.
Find relevant code paths with Jev-guided traversal of a repository.
Rank a collection of texts through Jev-judged pairwise tournaments.
Score OpenTelemetry records before routing them to deeper analysis.
Use semantic predicates, scores, and routes in shell pipelines.
Ask typed Jev questions directly from the terminal.
Ask a yes/no question across the functions in a codebase.
Label the tone of Bluesky posts and drafts as you browse.
Track time-stamped Jev forecasts against later public market observations.
Review JavaScript and TypeScript comments for accuracy and usefulness.
A configurable CLI for sending state and typed questions to Jev.
Review whether cited papers support the sentences in a manuscript.
Inspect typed quality signals while drafting an X post.
Explore emoji suggestions and tone signals for the text you type.
Replace flagged Spanish words with beeps using timestamped transcripts.
Sort readable documents into categories with a review queue.
Reorder search candidates with one Jev relevance judgment per document.
Inspect a CV with structured, traceable Jev assessments.
Evaluate application input, output, and retrieved text with Jev checks.
Route Persian or English support tickets with Jev and explicit business rules.
Refine a draft against your writing samples with a Jev feedback loop.
Assess npm lifecycle scripts before deciding how to handle an installation.
Find files, map a subject, and trace references using Jev judgments.
Inspect suspicious text messages using Jev signals and adjustable policy.
Lint source comments against five Jev evaluation dimensions.
Review a folder of CVs with an editable scoring policy.
Explore Jev workflows for tickets, operational alerts, and deployment risk.
Hide page clutter with reusable, Jev-classified browser rules.
Delegate a bounded browser step to Jev through MCP.
Control macOS apps through accessibility targets chosen by Jev.
Bring Jev’s indexed action selection to the ego lite browser.
A compact Jev browser loop paired with a timed task benchmark.
Add Jev judgment labels to X posts and Hacker News comments.
One Playwright core exposed as a persistent CLI, SDK, and MCP server.
Explore native desktop control with Jev and an optional planning model.
Search and follow web evidence with Jev-ranked pages and links.
Inspect Jev browser decisions in a local visual control panel.
Let Jev drive browser steps and escalate uncertainty to the calling agent.
Run persistent Android tasks with Jev selecting valid device actions.
Add page checks and action judgment to an existing Playwright MCP setup.
Explore browser flows with Jev decisions and replayable test evidence.
Reorder Google results using Jev relevance and promotional-content judgments.
Optionally blur text flagged as advertising or AI-like prose.
Run browser goals through named actions and Jev selections.
Explore Jev tactical judgments inside a MuJoCo drone simulation.
Watch Jev pick from legal Snake moves with measured board features.
A structured-state controller for a StarCraft shareware mission.
Inspect the judgments behind guards in a stealth game.
Compare Jev-selected tactics inside two browser Doom instances.
Follow Jev decisions in an experimental Civilization II controller.
Use Jev to select individual Tetris actions from measured outcomes.
Race Jev at classifying messages as spam or not.
Switch a browser brick-breaker paddle between manual and Jev control.
Explore NPC decisions and shogi moves in one visual lab.
Inspect car-control judgments in a changing 3D road simulation.
Turn a robot-arm goal into a sequence of predefined motions.
Find a path between Wikipedia articles using Jev-ranked links.
A visual control lab for Jev across games and emulator backends.
Run Jev-versus-Jev gomoku with a MoonBit API client.
Let Jev choose serves and returns in a live browser table-tennis game.
Choose jump, duck, or run for each new dinosaur-game obstacle.
Ask Jev to choose a complete, collision-checked Tetris placement.
Compare parallel 2048 games while editing the state Jev receives.
Try to persuade a border inspector whose decisions come from Jev.
Drive a Pong paddle using symbolic state and Jev choices.
Watch Jev pilot an original river-shooter arcade game.
Experiment with rover missions, energy use, and inspectable decisions.
A social-deduction game concept with a Jev moderation prototype.
Inspect a customer-service agent’s action gate under adversarial testing.
Observe Jev controlling a small creature in a deterministic sandbox.
Watch two Jev players choose among legal chess moves.
Inspect Jev actions alongside a live Minecraft world view.
Use Jev for automatic model selection and typed evaluations in agents.
Send typed evaluation questions from shell scripts through AI Gateway.
Add a Jev decision companion to the Loki agent.
Display typed Jev answers and probability cards inside Agent Zero.
Route example email intents through an async LangGraph workflow.
Place Jev judgments in an HTTP inspection and forwarding service.
Integrate typed Jev requests into Laravel services and tests.
Ask Choice, Noul, and Score questions from PostgreSQL.
Add Jev configuration, usage records, and confidence policies to Rails.
Interpret Home Assistant voice commands with batched Jev questions.
Prototype Jev semantic checks for a Mellea generation loop.
Browse reusable React components for TypeSafe-style decision interfaces.
Use Jev to supervise evidence from a coding agent’s work.
Evaluate Pi edits and actions against project rules with Jev.
Route Codex turns through Jev-selected model and reasoning settings.
Reduce large Claude Code tool results using Jev relevance judgments.
Expose typed Jev judgments as composable commands for coding agents.
Inspect a pull request’s risk, review depth, and test gaps.
Delegate file ranking, change checks, and triage to bounded Jev workflows.
Use a single model route with Jev selecting from a provider catalog.
Pair a Pi coding model with Jev judgments and explicit action policies.
Route Claude Code requests while accounting for prompt-cache tradeoffs.
Inspect MCP calls, results, and tool descriptions with Jev.
Review proposed database migrations with typed Jev judgments.
Add Jev option scores and optional skill routing to Claude Code.
Evaluate agent tool calls for risk, user intent, and untrusted influence.
Add an advisory Jev reviewer to an OMP coding session.
Run an issue-to-PR loop with tests, an independent reviewer, and Jev checks.
Combine repository policy with semantic change-risk signals.
Check a coding agent’s stopping point against plain-language rules.
Review whether a Pi session openly left required work unfinished.
Add semantic checks and traceable review signals to a single Pi agent.
Combine Jev safety signals and model selection in an LLM gateway.
Check source files against natural-language coding conventions.
Suggest a relevant installed capability for the current agent prompt.
Route an OpenAI-compatible model ID through a Jev decision.
Use Jev as a typed decision layer within Pi.
Give a Hermes agent a typed Jev tiebreaker.
Return structured code-quality judgments to a coding agent over MCP.
Combine Zod shape validation with Jev semantic checks.
Typed System One clients and Microsoft.Extensions.AI adapters for .NET.
Call TypeSafe with inferred answer types from Swift applications.
Use named tuples for typed Jev questions and answers in Scala.
Ask batched Choice, Noul, and Score questions from Elixir.
A strictly typed PHP client with configurable transport and retries.
Infer Jev answer types from the questions defined in Zig.
A Ruby client for direct access to the System One API.
A Go System One client with optional Langfuse instrumentation.
Build typed decision workflows with Jev or a custom provider.
Bind a validated state schema and Jev questions into one typed artifact.
Turn a natural-language request into choices from a fixed UI catalog.
Read writing diagnostics through a playful compiler-style interface.
Evaluate a paper’s presentation, clarity, and completeness.
Apply your own typed questions to selected CSV rows.
Inspect separate Jev checks for clarity, filler, tone, and actionability.
Bring a CSV and inspect Jev classifications in a distribution chart.
Try another keyword or clear your filters.