What is the 'Neural Link'?

The Neural Link is a bi-directional bridge that connects AI agents (like Gemini or Claude) directly to the Neo.mjs runtime. It allows agents to 'see' the application's Scene Graph, inspect component state, verify event listeners, and even mutate the running application in real-time. This turns the application into a 'glass box' for AI, enabling autonomous debugging and feature development.

Why is Neo.mjs called an 'Application Engine' instead of a framework?

Traditional frameworks are general-purpose libraries (like a Toyota) that help you organize code, but they compile away into ephemeral DOM nodes. Neo.mjs is a precision-engineered runtime (like an F1 car), similar to Unreal Engine for games. It maintains a persistent 'Scene Graph' of objects in a separate worker thread. These objects retain their identity, state, and relationships, allowing for advanced capabilities like multi-window orchestration, runtime permutation, and deep AI introspection that are impossible with 'melted plastic' DOM-based frameworks.

What is 'Context Engineering'?

Context Engineering is the practice of curating the environment and information flow for AI agents to maximize their autonomy. In Neo.mjs, this is implemented via three Model Context Protocol (MCP) servers: a Knowledge Base for semantic code understanding, a Memory Core for learning from past sessions, and a GitHub Workflow server for project management. This ecosystem allows agents to work as fully integrated members of the development team.

What is 'Object Permanence' in the context of Neo.mjs?

In Neo.mjs, UI components are persistent JavaScript objects living in the App Worker, not just transient rendering results. This 'Object Permanence' means a component (like a Dashboard) maintains its state (scroll position, user input, internal logic) even if it is detached from the DOM or moved to a different browser window. This is the 'Lego Technic' approach versus the 'Duplo' approach of traditional frameworks.

What is an 'Agent Operating System'?

Neo.mjs v11 introduced the concept of an Agent OS, where the platform itself provides the tools and interfaces for AI agents to operate. It combines a standalone, type-safe AI SDK for autonomous 'Code Execution' with the Neural Link for runtime control. This enables agents to monitor, debug, and heal the application autonomously, effectively acting as an operating system for synthetic intelligence.

How does Neo.mjs handle multi-window applications?

Neo.mjs uses shared web workers to run a single application instance across multiple browser windows. All windows share the same application state and data in real-time. Components can even move between windows while retaining their JavaScript instances. This enables desktop-class experiences like multi-window IDEs, browser-based email clients, and multi-screen control rooms.

What makes Neo.mjs different from React, Angular, or Vue?

Neo.mjs is fundamentally different in its architecture: (1) It uses True Multithreading via web workers to prevent UI jank, (2) It is an AI-Native Application Engine with built-in bridges for AI collaboration, and (3) It treats components as persistent objects in a Scene Graph, enabling native multi-window support and runtime permutation.

Frontmatter

id	7308
title	Create "Working with AI Agents" Guide
state	Closed
labels	documentationenhancement
assignees	tobiu
createdAt	Sep 29, 2025, 9:52 AM
updatedAt	Sep 29, 2025, 11:55 AM
githubUrl	https://github.com/neomjs/neo/issues/7308
author	tobiu
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Sep 29, 2025, 11:12 AM

Create "Working with AI Agents" Guide

Name: Neo.mjs Application Engine
Author: Neo.mjs

Closed v11.0.0 documentationenhancement

tobiu commented on Sep 29, 2025, 9:52 AM

Create a new guide, WORKING_WITH_AGENTS.md, to provide comprehensive instructions for human developers on how to effectively and safely collaborate with AI agents within this repository.

This guide covers several critical topics:

Session Initiation: How to start a session correctly by directing the agent to AGENTS.md.
Error Recovery: How to guide an agent to recover from mistakes.
Agent Behavior: An explanation of non-determinism and accuracy, setting the right expectations.
The "Golden Rule": A critical safety rule about never using "Always Allow" for file modifications, backed by security research on agentic misalignment.
Panic Responses: How to spot and handle destructive agent behavior.
The Session Lifecycle: An analogy for understanding agent context degradation over time.
Proactive Context Management: A best practice for knowing when to start a fresh session.

tobiu assigned to @tobiu on Sep 29, 2025, 9:52 AM

tobiu added the documentation label on Sep 29, 2025, 9:52 AM

tobiu added the enhancement label on Sep 29, 2025, 9:52 AM

tobiu referenced in commit c9fcd8b - "Create "Working with AI Agents" Guide #7308 WIP" on Sep 29, 2025, 9:53 AM

tobiu referenced in commit 8e9fe96 - "#7308 write file tool" on Sep 29, 2025, 9:57 AM

tobiu referenced in commit 5d21ade - "#7308 dealing with panic responses" on Sep 29, 2025, 10:01 AM

tobiu referenced in commit 21f91f7 - "#7308 human lifetime analogy" on Sep 29, 2025, 10:22 AM

tobiu referenced in commit c2bbd70 - "#7308 agentic misalignment" on Sep 29, 2025, 10:29 AM

tobiu referenced in commit 0ed12fd - "#7308 proactive context management" on Sep 29, 2025, 10:33 AM

tobiu referenced in commit 57e2413 - "#7308 Fully Automated Workflows" on Sep 29, 2025, 10:54 AM

tobiu referenced in commit 8d007c1 - "#7308 Fully Automated Workflows" on Sep 29, 2025, 10:54 AM

tobiu referenced in commit f290c87 - "#7308 final polishing" on Sep 29, 2025, 11:08 AM

tobiu closed this issue on Sep 29, 2025, 11:08 AM

tobiu reopened this issue on Sep 29, 2025, 11:11 AM

tobiu referenced in commit 2efbcef - "#7308 final polishing" on Sep 29, 2025, 11:12 AM

tobiu closed this issue on Sep 29, 2025, 11:12 AM