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	8598
title	Refine Chimera safeguard in VDom.syncVdomState
state	Closed
labels	enhancementaicore
assignees	tobiu
createdAt	Jan 13, 2026, 2:59 PM
updatedAt	Jan 13, 2026, 3:08 PM
githubUrl	https://github.com/neomjs/neo/issues/8598
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 13, 2026, 3:08 PM

Refine Chimera safeguard in VDom.syncVdomState

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

Closed v11.21.0 enhancementaicore

tobiu commented on Jan 13, 2026, 2:59 PM

Currently, VDom.syncVdomState aborts completely if the root node tags mismatch (e.g. div vs ul). This prevents child nodes from synchronizing their IDs/state, leading to unnecessary DOM destruction and recreation when a wrapper tag changes.

The fix is to refine the safeguard:

Skip property synchronization (ID, scrollTop) for the mismatched node itself.
Continue recursion to attempt synchronization of child nodes (which will have their own tag checks).

tobiu added the enhancement label on Jan 13, 2026, 2:59 PM

tobiu added the ai label on Jan 13, 2026, 2:59 PM

tobiu added the core label on Jan 13, 2026, 2:59 PM

tobiu referenced in commit ffb9f5c - "enhancement: Refine Chimera safeguard in VDom.syncVdomState (#8598) on Jan 13, 2026, 3:03 PM

tobiu assigned to @tobiu on Jan 13, 2026, 3:03 PM

tobiu Jan 13, 2026, 3:03 PM

Input from Gemini 3 Pro:

✦ I have refined the safeguard in VDom.syncVdomState. It no longer aborts completely on tag mismatch. Instead:

It skips syncing ID/Scroll for the mismatched node (preventing Chimera on the parent).

It continues to recurse into children, allowing them to sync their IDs if their tags match.

This enables child node preservation (moving) when a parent tag changes. Changes pushed to dev.

tobiu referenced in commit 0725b71 - "enhancement: Preserve scroll state during tag name changes (#8598) on Jan 13, 2026, 3:06 PM

tobiu Jan 13, 2026, 3:07 PM

Input from Gemini 3 Pro:

✦ I have expanded the scope of this ticket to include Scroll State Preservation during Tag Changes.

Originally, VDom.syncVdomState prevented any state synchronization if a tag mismatch was detected to avoid "Chimera" node corruption (e.g., a ul receiving a li ID). However, this had the side effect of also preventing scroll state synchronization (scrollTop, scrollLeft), causing scroll jumps when a container's tag was changed (e.g., div -> section).

Updates:

src/util/VDom.mjs:

Refined the safeguard: I moved the scroll synchronization logic outside the !tagMismatch block.

Result: The worker/VDOM now correctly captures and preserves the scroll position from the old VNode even if the new VDOM has a different tag name. The ID synchronization remains protected inside the safeguard to prevent Chimera corruption.

src/main/DeltaUpdates.mjs:

Updated changeNodeName to explicitly copy scrollTop and scrollLeft from the old DOM node to the new clone before replacement.

Result: The physical DOM replacement operation is now seamless regarding scroll position.

These changes ensure that semantic tag changes are non-destructive to both child structure and scroll state.

tobiu closed this issue on Jan 13, 2026, 3:08 PM