Agent Decisions

Local browser automation workbench with an Edge/Chrome sidebar and Codex MCP sharing one Jev-driven task engine, with user confirmation.

MCP wingman that hands an agent's browser clicks and typing to Jev on a real logged-in Chromium, alongside Playwright MCP.

MCP server with record and recall tools: facts are logged during a session and Jev keeps only those relevant to the next task.

iOS custom keyboard that shows a copied message's intent, risk level and candidate replies inside any chat app, filling but never sending.

Windows desktop chat assistant that OCRs a selected chat region, has Jev analyse the conversation, and ranks drafted replies for copying.

Framework-independent participation gate letting group-chat agents answer untagged questions only when Jev finds a useful reason to join.

macOS chat overlay that reads the current chat window and shows the incoming message's intent, risk and candidate replies, read-only.

Unofficial fork of jev-chat-windows: WeChat overlay with local OCR and drafted replies, adding optional auto-send and a knowledge base.

WeChat reply assistant fork: DeepSeek drafts three replies, Jev pre-judges, reviews and ranks them; auto-send is cancellable.

Fork of the jev-chat Windows app adding a key-free local LAYA judgment backend and a DPI-aware screen capture fix.

Chrome side-panel extension where Jev drives the current tab toward a typed goal, or answers quick questions about highlighted text.

Local gateway and MCP tools that let Jev predict which tool a coding agent should call next, from suggestions to enforced choices.

Claude Code plugin adding typed Jev decisions to hooks: task kind, command risk, failure class, completion; never grants permissions.

Codex plugin adding a bounded Jev decision loop to Computer Use for browser tabs and native macOS apps.

Windows MCP server and CLI where Jev observes windows and chooses controls so agents can hand off whole desktop tasks.

TypeScript browser agent for ego lite where one Jev request picks the operation and indexed target element each step.

Local gateway for coding agents that asks Jev which tool to call next and passes everything else to your usual model.

Python harness for open-ended goals: AI-authored tools and checks, Jev choosing the next tool and arguments from fresh state.

Codex browser plugin where Codex prepares inputs and Jev quickly picks each next action in local Chrome.

Claude Code job-application tool that finds roles, fills forms in Chrome, reads every answer back and sends only those you approve.

Codex skill and MCP for advisory Jev decisions in Java/Maven backend work: file relevance, change risk, SQL risk and more.

Maps each Python function to the tests that run it; Jev scores candidate function-test links that static analysis misses.

Jev browser agent that pierces shadow DOM and iframes, adds canvas fallback and full actions, with one Jev request per cycle.

MCP server that lets Claude Code or Codex drive real Chrome with Jev picking elements and checking steps, plus safety gates and traces.

Durable Android sub-agent: a SQLite-backed worker observes the UI and Jev picks among valid actions, with verification and escalation.

Fork of mobile-mcp that adds OCR and lets Jev pick which recognised text element to tap on Android and iOS devices.

Claude Code mod that hands small decisions (routing, skill choice, screening, gating, trimming) to Jev or another decision backend.

Runs Claude Code on Opus 5.5 with Jev re-picking reasoning effort after every tool batch, via per-message effort so the cache survives.

CLI where several coding agents draft implementation plans and Jev scores them, decides on cross-review and picks the finaliser.

Claude Code (and Codex) plugin that trims long Bash output chunk by chunk with Jev before it reaches the model, without summarising.