Agent Decisions

Codex port of fast-jev-compaction that re-injects Jev-selected verbatim history after compaction; the author advises against using it.

OpenCode V2 port of fast-jev-compaction that asks Jev or a local Jev-style model which old tool outputs still matter.

Windows file organiser that uses Jev Choice and Noul to suggest which folder a new file belongs in and to drill down to find files.

Windows desktop assistant that reads UI Automation controls and has Jev choose each action, pausing for approval before irreversible steps.

Rebuild of the goodvibes agent platform where Jev is targeted to make every semantic decision, with outcomes act, revise, defer or reject.

Screenshot-in, coordinate-out harness where Jev picks among vision-described grid tiles recursively, with probability and margin gates.

Self-hosted helper for tricky chats and everyday decisions: Jev makes typed checks, an LLM handles language, the user decides.

Decision engine that combines Jev probability distributions with loss matrices to decide when a clarifying question is worth asking.

Python browser agent where Jev picks each operation and element in about 150 ms, escalating to an LLM only when unsure.

Gives an agent one tool that uses Jev to search a nested capability tree and return only the documented commands a task needs.

Coding agent where Jev handles context selection, tool routing, plan gating and verification, and the big model sees only key context.

Chat-shaped command bar where Jev picks the tool, arguments, confirmation and reply type, and code builds replies only from tool data.

Windows and Chrome GUI delegation for Codex: a local controller runs a task contract, calling Jev only for semantic choices.

Talk to your Mac: local whisper.cpp transcribes, one Jev request picks the action and typed arguments, and code executes macOS automation.

Floating macOS bar for voice or text commands where Jev picks the next action from live accessibility controls in a loop.

Python agent development kit for building System One pipelines with Jev for guardrails, routing and PR triage.

Local web and voice interface for Codex and Claude sessions in tmux, where Jev interprets each request and Python performs it.

Skill and CLI that compares a shortlist of agents, MCP servers or skills against a task and permission ceiling, abstaining on weak leads.

Job-application skill with memory that fills forms from your résumé, using Jev to decide what your record supports and leaving gaps open.

Self-hosted Feishu bot and web workbench for Jev choices with probabilities, plus experimental word-by-word writing.

Local browser automation UI where Jev chooses bounded page actions, Browser Harness executes them, and a text model only fills fields.

Hybrid TypeScript browser harness: an LLM plans verifiable subgoals, Jev picks each action and DOM field, Playwright acts.

Readable reference skill for Claude Code and Codex where Jev picks from a numbered table of page controls, with an explainer site.

Agent skill and local jb command that drive an isolated Playwright Chromium, with Jev choosing in-page actions for a narrow goal.

Grok skill that uses Jev as a judgment sensor in a builder-agent loop, mixing its probabilities with priors before choosing the next act.

Stanley: a Jev-first coding CLI where Jev routes requests to deterministic workflows and an agent only writes new workflows when none fits.

Multi-agent Codex factory: Jev decides task shape, decomposition and routing, and failures are classified, not blindly retried.

Claude Code compaction plugin where Jev decides per old tool result whether to keep it verbatim or move it to a drawer file.

Codex computer-use skill where Jev picks the next on-screen element, action, completion and risk from text candidates.

Depth-crawling research agent where Jev makes every per-page relevance and next-link decision and an LLM only plans and writes.