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	9158
title	docs: Document Grid Performance Optimizations (Row/Cell Recycling)
state	Closed
labels	documentationaiperformance
assignees	tobiu
createdAt	Feb 15, 2026, 1:32 AM
updatedAt	Feb 15, 2026, 1:35 AM
githubUrl	https://github.com/neomjs/neo/issues/9158
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 15, 2026, 1:35 AM

docs: Document Grid Performance Optimizations (Row/Cell Recycling)

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

Closed v12.0.0 documentationaiperformance

tobiu commented on Feb 15, 2026, 1:32 AM

The recent performance optimizations for the Grid (#9156 and #9157) introduced significant logic changes to Neo.grid.Body and Neo.grid.Row. These changes need to be reflected in the JSDoc to ensure future maintainability and understanding of the "Row Skipping" and "Cell Recycling" strategies.

Changes:

Neo.grid.Body.createViewData: Document the force parameter and the auto-detection logic for horizontal scrolling/resizing. Explain the three optimization strategies (Row Skipping, Cell Recycling, Forced Updates).
Neo.grid.Row.createVdom: Document the "Cell Recycling" strategy, specifically how the recycle flag and oldCn Map lookup work to prevent redundant cell re-rendering during horizontal scrolling.
Neo.grid.Row.updateContent: Ensure the params force and recycle are well-documented. (Already done in implementation, but good to double-check consistency).

tobiu added the documentation label on Feb 15, 2026, 1:32 AM

tobiu added the ai label on Feb 15, 2026, 1:32 AM

tobiu added the performance label on Feb 15, 2026, 1:32 AM

tobiu referenced in commit 044adec - "docs: Document Grid Performance Optimizations (Row/Cell Recycling) (#9158)" on Feb 15, 2026, 1:34 AM

tobiu assigned to @tobiu on Feb 15, 2026, 1:34 AM

tobiu Feb 15, 2026, 1:34 AM

Input from Gemini 3 Pro:

✦ I have updated the JSDoc for Neo.grid.Body.createViewData and Neo.grid.Row.createVdom to accurately reflect the new optimization strategies.

Documentation Enhancements:

Row Skipping: Documented how createViewData and Row.updateContent collaborate to skip VDOM generation when state hasn't changed.

Cell Recycling: Added a detailed explanation of the Map-based cell recycling strategy within Row.createVdom. I structured this as a sub-section of the "Pooled Cells" phase to maintain logical flow.

Forced Updates: Clarified the role of the force parameter and the auto-detection logic for horizontal scrolling/resizing.

This ensures the codebase is self-documenting regarding these critical performance optimizations.

tobiu closed this issue on Feb 15, 2026, 1:35 AM