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	8956
title	Refactor: Move `defaults` Serialization to `ComponentColumn.toJSON`
state	Closed
labels	airefactoringcore
assignees	tobiu
createdAt	Feb 2, 2026, 11:58 PM
updatedAt	Feb 3, 2026, 12:00 AM
githubUrl	https://github.com/neomjs/neo/issues/8956
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 3, 2026, 12:00 AM

Refactor: Move `defaults` Serialization to `ComponentColumn.toJSON`

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

Closed v12.0.0 airefactoringcore

tobiu commented on Feb 2, 2026, 11:58 PM

Goal

Consolidate the toJSON serialization logic for defaults into Neo.grid.column.Component to avoid code duplication in subclasses.

Scope

Update src/grid/column/Component.mjs:
- Modify toJSON to include defaults, using me.serializeConfig(me.defaults) if it exists.
Update src/grid/column/Sparkline.mjs:
- Remove the overridden toJSON method.
Update src/grid/column/Progress.mjs:
- Remove the overridden toJSON method.

Motivation

Both Sparkline and Progress columns override toJSON solely to serialize the defaults config. Moving this to the base class Neo.grid.column.Component DRYs up the code and ensures all component columns serialize correctly by default.

tobiu added the ai label on Feb 2, 2026, 11:58 PM

tobiu added the refactoring label on Feb 2, 2026, 11:58 PM

tobiu added the core label on Feb 2, 2026, 11:58 PM

tobiu referenced in commit 322d0b5 - "refactor: Move defaults Serialization to ComponentColumn.toJSON (#8956)" on Feb 3, 2026, 12:00 AM

tobiu assigned to @tobiu on Feb 3, 2026, 12:00 AM

tobiu Feb 3, 2026, 12:00 AM

Input from Gemini 3 Pro:

✦ I have successfully moved the defaults serialization logic to the base class Neo.grid.column.Component.

Changes:

Updated Neo.grid.column.Component: The toJSON method now checks for me.defaults and serializes it if present. This ensures that any component column utilizing defaults will have them correctly passed to the Neural Link.

Cleaned up Subclasses: Removed the redundant toJSON overrides from both Neo.grid.column.Sparkline and Neo.grid.column.Progress.

This refactoring reduces code duplication and ensures a consistent behavior for all component columns.

tobiu closed this issue on Feb 3, 2026, 12:00 AM

Refactor: Move defaults Serialization to ComponentColumn.toJSON

Goal

Scope

Motivation

Refactor: Move `defaults` Serialization to `ComponentColumn.toJSON`