Agent Decisions

Verified computer-use agent: a Jev guard checks claimed completions and gates irreversible actions; Jev also takes simple steps.

Local compaction proxy for Claude Code and Codex that compacts more often with local rules and keeps full history searchable.

Local-first Windows writing studio with knowledge graphs and author voice, where optional Jev evaluates candidates and editorial decisions.

Skill pack handing an agent's small decisions to Jev: model routing, skill choice, search, memory, compaction and computer use.

Intent compiler skill that turns vague coding requests into a typed IntentSpec, with Jev or LAYA as optional decision backends.

Goal-driven browser agent where each step is one Jev choice over the page's controls, then reviews the run for root causes.

Standalone Node studio for building and testing workflows of typed Jev judgments with code-owned decisions, plus games and simulations.

Chrome extension port of Jev Ultrafast that drives your current tab, with Jev picking the operation and element each step.

Native macOS computer-use loop: local OCR and accessibility find controls, Jev picks the next action from a finite list.

MCP tool that asks Jev which files, web pages or snippets are relevant to a query, so the agent reads selectively.

Browser Use's browser agent where Jev picks an operation and page element in one request and a small LLM only writes text to type.

Coding-agent hook where Jev decides whether a mid-turn message should steer the running task, be queued, or interrupt it.

MCP server that lets agents observe and control Android phones over ADB, with Jev picking controls and judging goal completion.

Bounded browser execution for parent agents: Jev picks the next typed action, agent-browser runs it, stuck states hand back.

Typed judgment layer for Claude Code, Codex and Hermes Agent: deterministic facts in code, language judgments in Jev, with receipts.

Chinese-language agent skill that offloads classify, screen, score and compliance checks to Jev via OpenCode Zen's free tier.

Portuguese-language agent skill for millisecond Jev decisions via OpenRouter, with validation, an MCP mode and calibration evals.

One skill and MCP server for Claude Code, Codex and Hermes where Jev gates large-model turns, routes models and guards Git steps.

Skill that makes Claude Code and Codex split AI features into Jev, LLM or plain-code steps before writing code.

Claude Code PreToolUse hook that auto-approves shell commands Jev is confident are read-only, and otherwise shows the normal prompt.

Open-source Jev skills for Claude Code, Codex, Cursor and Grok: one client to gate, route, guard, verify, triage, review and act.

Helpers for browser-harness that let Claude Code or Codex hand off a whole website sub-task in one call, with Jev deciding each step.

Agent-plugin browser tool where Jev picks one operation and one row from a numbered page table; a small LLM only writes typed text.

Browser automation CLI with an interactive terminal and structured commands for agents, using Jev decisions and agent-browser execution.

Plugs any CDP browser, including engines that never draw a page, into a Jev loop that picks operations and targets from the DOM.

Chrome extension plus MCP server so Claude or Codex can drive your real Chrome, with Jev picking each click in about half a second.

Python decision layer for browser and desktop automation: code observes, acts and verifies; the model makes one typed choice per step.

Chinese-language Codex skill adapted from jev-ultrafast that lets Codex hand multi-step Chrome tasks to Jev with preset inputs.

Browser and computer use for coding agents via CLI and MCP, with Jev's calibrated judgments and a code-owned control loop.

Codex browser skill where Jev handles navigation, clicks, toggles and scrolling while Codex handles text input and verification.