Agent Decisions

On-device Android agent that taps any app, with an allow/confirm/block safety gate optionally backed by Jev or Laya.

Phone agent where Jev picks one operation and one element from an indexed accessibility table; code does the tap.

Rust template for multi-agent orchestration with Jev as the L0 layer for typed routing, risk and escalation decisions.

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

OMP extension keeping one endless chat as a summary tree, with five Jev judge gates for rules, prefetch, compression, tools and recall.

Desktop computer-use agent for macOS and Windows where Jev chooses each concrete native action, with optional GPT-6 Astra planning.

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

Pilot that puts Jev into LangGraph routing and Deep Agents guardrails and claim verification, with executed notebooks and caveats.

PlayJev (filedcom): Stagehand-style natural-language browser automation for Playwright where Jev makes the browser decisions.

Toy research agent where Jev makes every keep/skip and delve decision over search results, and one expensive call writes the report.

Educational email agent where Jev picks each message's label, reply need and family flag before drafting.

Local context-pruning proxy for Claude Code and Codex where Jev decides which history spans can be safely omitted.

Chat copilot for Mac, Windows, Android and an iOS keyboard that reads chats, judges with Jev or DeepSeek and drafts replies.

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.

Locates the file a bug report is about, or flags defects in a diff, by asking Jev yes/no over small source batches.

Agent memory system where Jev or local Laya controls memory organisation, query routing, retrieval budgets and stopping.

Archived Go harness finding Jev tool steering does not reliably cut agent tokens in Claude Code or Codex; context trimming helped.

Research code evaluating Jev as an independent per-tool relevance judge for building task-level tool spaces on TGB, BFCL and GTA.

Open 2B browser-agent decision model fine-tuned from MiniCPM5 that serves the System One protocol for jev-ultrafast.

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.

Builds auditable decision trees and runnable decision SOPs from data and a natural-language goal via LLM features and information gain.

Coding agent that runs discriminative Monte Carlo Tree Search, with Gemini proposing actions and Jev Choice and Score guiding the search.

Production control plane for OpenClaw agents: Jev routes each Slack message to its task, with Temporal workflows, an evaluator and memory.

Local social research agent: Jev picks each bounded Instagram, TikTok or LinkedIn step and socai CLI runs it in your Chrome.

Browser extension and MCP server where Aside observes the page and Jev picks the next action from defined candidates.

Natural-language CLI where Jev picks which installed 'reflex' programs a sentence calls, running them only when sure enough.

Fork of fast-jev-compaction adding env-configurable endpoints, a CLI, an MCP server and a Devin post-compaction restore hook.