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	9481
title	Auto-detect `isTreeGrid` config based on the Store instance
state	Closed
labels	enhancementaigrid
assignees	tobiu
createdAt	Mar 15, 2026, 7:54 PM
updatedAt	Mar 15, 2026, 7:55 PM
githubUrl	https://github.com/neomjs/neo/issues/9481
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Mar 15, 2026, 7:55 PM

Auto-detect `isTreeGrid` config based on the Store instance

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

Closed v12.1.0 enhancementaigrid

tobiu commented on Mar 15, 2026, 7:54 PM

Currently, developers are forced to manually set isTreeGrid: true on Neo.grid.Container when using a TreeStore (as seen in examples/grid/tree/GridContainer.mjs and examples/grid/treeBigData/GridContainer.mjs).

Since a TreeGrid relies entirely on a TreeStore for its hierarchical logic, we can improve the DX by auto-detecting this state.

This enhancement modifies afterSetStore() in src/grid/Container.mjs to automatically set me.isTreeGrid = value?.isTreeStore === true, eliminating the need for manual configuration and ensuring ARIA roles are always correct even if the store changes dynamically.

In addition, it applies the "Anchor & Echo" Knowledge Base Enhancement Strategy to the store_ configs in both grid.Container and grid.Body, clarifying their support for both flat stores and hierarchical TreeStore instances, and fixes copy-paste JSDoc typing errors for the afterSetStore method params.

tobiu added the enhancement label on Mar 15, 2026, 7:54 PM

tobiu added the ai label on Mar 15, 2026, 7:54 PM

tobiu added the grid label on Mar 15, 2026, 7:54 PM

tobiu referenced in commit 938d435 - "feat(grid): Auto-detect isTreeGrid config based on the Store instance (#9481)" on Mar 15, 2026, 7:55 PM

tobiu assigned to @tobiu on Mar 15, 2026, 7:55 PM

tobiu Mar 15, 2026, 7:55 PM

Input from Gemini 3.1 Pro:

✦ I have implemented the auto-detection of isTreeGrid based on store.isTreeStore within afterSetStore for the Grid Container. The manual isTreeGrid config has been removed from the relevant examples (examples/grid/tree and examples/grid/treeBigData). Additionally, JSDocs for the store_ and afterSetStore methods in both Container.mjs and Body.mjs have been enhanced to apply the "Anchor & Echo" strategy, correcting type definitions and adding broader conceptual context. Code has been committed and pushed.

tobiu closed this issue on Mar 15, 2026, 7:55 PM