Agent Decisions

Fast browser-use layer for coding agents: Jev picks the operation and target element each step, via MCP server or CLI.

chrome-devtools-mcp plus one 'reach' tool: Jev walks the browser to the right spot so the agent makes a single devtools call there.

Filters an assistant's memories by relevance, not resemblance: one Jev yes/no per memory in a single request, kept above a threshold.

Claude Code plugin where Jev asks one yes/no per standing rule and delivers only the rules relevant to each prompt, once per session.

Fast iOS Simulator and Android navigator built on sim-use where Jev picks each tap instead of a frontier-model turn.

Scores installed Claude Code skills against the current project with Jev and hides irrelevant ones via skillOverrides.

Pre-message hook that keeps or drops SKILL.md files before the first model call, using local overlap or Jev keep/drop judgments.

Claude Code and Codex plugin that removes skills from context and lets Jev decide each turn which SKILL.md bodies to inject.

Fourteen opt-in Claude Code and Codex skills where Jev makes one bounded choice: which skill, model, test, file or next step.

Test-failure triage for coding agents: local rules first, then one batched Jev call labels failures RETRY, FIX_CODE or FIX_ENV.

Chinese UI test framework where Jev scores candidate page elements for each step of a natural-language test case.

MCP server that takes a whole browser task (URL, goal, checks) in one call and drives Chrome server-side with a decision model.

Android chat co-pilot that reads the active chat via Accessibility and returns typed verdicts on intent, emotion and risk; never replies.

Manifest V3 Chrome port of jev-ultrafast that drives your current tab, with Jev choosing each operation and element.

Terminal coding agent where an LLM reads, edits and runs code, and Jev makes a few optional side decisions.

Cucumber runner where Jev resolves each Gherkin step against the live page and Playwright executes it, so tests need only the .feature file.

Flutter integration-test package where Jev picks the next registered UI action and judges whether the test goal is reached.

Python agent runtime where Jev Choice decisions pick tools and arguments, and low-confidence picks go to an LLM for review.

Project memory for Claude Code that asks Jev whether each chat statement is worth keeping and checks tool calls against saved rules.

Local memory for coding agents that stores verbatim quotes and has Jev grade memory lines as keep, stale, wrong or unsupported.

Prunes long command output for coding agents by asking Jev which lines matter for the task, keeping original text and order.

Open-source desktop browser agent where a language model plans, Jev chooses the executable action and Chromium carries it out.

Toolkit where Jev condenses large MCP responses for Claude Code and maps Codex requests to reviewed, fixed repository operations.

Agent skill that has Jev pick the few relevant lines from big logs before your coding agent reads them, with a reversible reduce and ledger.

Plain-English end-to-end tests for Android and iOS apps where Jev works out the taps and a lockfile replays every decision exactly.

Browser tests written as user steps: Jev finds each control once, the path is recorded, and replays run without the model.

Fast Rust terminal coding agent with 44 providers that can ask Jev for its own decisions through a bundled client.

Voice assistant daemon for Hyprland Linux desktops that acts through tool modules, with Jev gating which requests and actions proceed.

Decision middleware for AI agents that uses local Laya to pick tools and judge results, falling back to an LLM when unsure.

Self-improving multi-platform agent harness with an optional Jev companion for typed judgments and per-session model routing.