Agent loop control with decision models

Chinese multi-seat exploration engine for game and rule-system design; Jev only gates whether to start deep exploration or ask.

Pi coding agent extensions, including pi-jev-router, which asks Jev whether a prompt should continue, fork or start a new session.

GitHub Action where an AI agent turns an issue into a PR behind guards, checks, a reviewer and a Jev gate that escalates when unsure.

Event-driven multi-agent network where Jev watches live state and assigns pending tasks to idle general-purpose agents.

Pi coding harness where any LLM writes and Jev returns typed reflex scores that policy code turns into allow, confirm, block, warn or steer.

Go macOS controller where Jev picks the next accessibility action, the target element and whether the goal is done.

DeepSeek Harness plugin for budgeted, read-only GPT 'teacher' consults; Jev may only suggest when a consult is worthwhile.

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

Python router that has Jev classify Grok Bot requests before costly work, returning actions like reuse_cache, stop_retry or ask_human.

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.

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

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

Gateway that batches agent control questions through Jev and calls a generative LLM only when policy says generation is needed.

Node experiment where Jev picks the next step around a coding agent, with approved actions and Codex or Claude Code delegation.

Windows UI Automation backend for arc-cua that lets a planner hand off desktop subtasks to a Jev-driven click-and-type loop.

General-purpose agent loop where Jev chooses each tool call and its arguments and Jot executes it until a reply is ready.

Playbook for using Jev as a cheap gate before expensive agent steps: confidence policy, question recipes, a skill and a router.

Hermes Agent skill that turns an intention into a checkable finish line, with shell checks and Jev judging the fuzzy requirements.

Claude Code skill that splits work into PBIs for Codex, Antigravity or Claude sub-agents, using Jev for model choice and triage.

Windows desktop gateway wrapping a local Qwen2.5-Coder 1.5B for agent loop-exit, extraction and scan checks plus a /v1/systemone shim.

Experimental protocol that checks the evidence behind a worker agent's PASS or BLOCKED report, with Jev answering narrow evidence questions.

Language and VM for long-running agent programs that pause for approval, resume after restarts and replay, with typed decision cells.

Reference framework where Jev picks a concrete computer-use action and its execution route from legal, verifiable candidates.

Research runtime where every agent step is a bounded typed decision, with a paged virtual option space over tools and memory.

Experiment using Jev Noul judgments on accumulated evidence to decide when Zilliz's DeepSearcher agent should stop searching.

Craftax survival agent where Jev picks one Choice per step from code-listed actions, with optional LLM goals, plus ablations.

Mineflayer Minecraft bot where code lists feasible actions and Jev picks one in about 0.2 s; 15 of 40 runs reached the Nether.

Minimal agent loop where Jev selects each action and approves tool calls, a chat model fills arguments, and MCP tools execute.

An LLM writes a task-specific Jev harness, improved with rewards and traces; a Pokemon harness rose from 25% to 75% wins.