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	8500
title	Enhance JSDoc for Neo.tree.List
state	Closed
labels	documentationai
assignees	tobiu
createdAt	Jan 10, 2026, 2:54 PM
updatedAt	Jan 10, 2026, 3:00 PM
githubUrl	https://github.com/neomjs/neo/issues/8500
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 10, 2026, 3:00 PM

Enhance JSDoc for Neo.tree.List

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

Closed v11.20.0 documentationai

tobiu commented on Jan 10, 2026, 2:54 PM

This task involves enhancing the documentation for Neo.tree.List in src/tree/List.mjs to align with the Knowledge Base Enhancement Strategy.

Goals:

Add a comprehensive @summary tag to the class-level JSDoc.
Provide a detailed description of the class's purpose, including its hierarchical nature, sticky header support, and drag-and-drop capabilities.
Add @see links to relevant examples or base classes.
Include keywords like Hierarchical Data, Tree View, Recursive List, and Sticky Headers to improve discoverability.

This will make the component easier to understand for both developers and AI agents.

tobiu added the documentation label on Jan 10, 2026, 2:54 PM

tobiu added the ai label on Jan 10, 2026, 2:54 PM

tobiu assigned to @tobiu on Jan 10, 2026, 2:54 PM

tobiu referenced in commit c91839f - "docs: Enhance JSDoc for Neo.tree.List (#8500) on Jan 10, 2026, 2:59 PM

tobiu Jan 10, 2026, 2:59 PM

Input from Gemini 3 Pro:

✦ I have applied the Knowledge Base Enhancement Strategy to Neo.tree.List in src/tree/List.mjs.

Documentation Enhancements:

Class-Level JSDoc: Added a comprehensive @summary and detailed description covering:

Recursive rendering architecture.

Sticky header functionality (native CSS + JS state detection).

Drag-and-drop capabilities.

Filtering logic.

Added relevant keywords for discoverability.

createItem: Added detailed docs explaining its role as the core VDOM factory, covering class assignment, hierarchy visualization (z-index/padding), and sticky positioning calculations.

createItemLevel: documented the recursive logic for transforming the flat store into a hierarchical DOM structure.

createItems: Documented as the main entry point for the rendering process.

saveScrollPosition & onScrollCapture: Refined comments to clearly explain the intent behind the scroll monitoring (detecting "stuck" states for visual styling).

These changes significantly improve the discoverability and understandability of the component for both human developers and future AI sessions.

tobiu closed this issue on Jan 10, 2026, 3:00 PM