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	8992
title	Implement Hybrid Cell Buffering (Pooling) for Grid Rows
state	Closed
labels	enhancementaiperformance
assignees	tobiu
createdAt	Feb 4, 2026, 10:13 PM
updatedAt	Feb 4, 2026, 11:49 PM
githubUrl	https://github.com/neomjs/neo/issues/8992
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 4, 2026, 11:49 PM

Implement Hybrid Cell Buffering (Pooling) for Grid Rows

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

Closed v12.0.0 enhancementaiperformance

tobiu commented on Feb 4, 2026, 10:13 PM

Problem

The current Neo.grid.Row implementation generates cell IDs based on the column dataField. During horizontal scrolling, this causes DOM nodes to be destroyed and created as they enter/exit the viewport.

This constant allocation/deallocation creates memory pressure (GC pauses) during rapid scrolling.

Solution: Hybrid Cell Pooling

Implement a pooling strategy to reuse cell containers.

1. Pooled Cells (Recycled)

Target: Columns with hideMode: 'removeDom'.
Mechanism: Fixed pool of cell containers (IDs: ...__cell-0, ...__cell-1).
Behavior: Recycle cells by updating style.left, cls, and content.
Impact on Child Nodes:
- Text/Homogeneous Content: If the new column has the same structure (e.g. plain text or same HTML structure), the inner nodes are also reused/updated. Zero GC.
- Heterogeneous Content: If the new column has a different structure, the inner nodes will be swapped by the VDOM engine. We still save the allocation of the heavy Cell Container (div.neo-grid-cell) and its layout positioning.

2. Permanent Cells (Stateful)

Target: Columns with hideMode: 'visibility' (e.g., Sparklines).
Mechanism: Keep data-bound IDs (...__firstname).
Behavior: Persist in DOM; toggle visibility.

Implementation Details

Neo.grid.Body: Implement getCellId(rowIndex, dataField) to handle pooled/permanent lookups.
Neo.grid.Row: Refactor createVdom for the hybrid pass.

Goal

Eliminate GC-induced micro-stutters by ensuring O(1) stability for the Grid Structure (Cell Containers).

tobiu added the enhancement label on Feb 4, 2026, 10:13 PM

tobiu added the ai label on Feb 4, 2026, 10:13 PM

tobiu added the performance label on Feb 4, 2026, 10:13 PM

tobiu referenced in commit 644fee5 - "feat: Implement hybrid cell pooling for Grid Rows (#8992)" on Feb 4, 2026, 11:41 PM

tobiu Feb 4, 2026, 11:42 PM

Input from Gemini 3 Pro:

✦ I have successfully implemented the Hybrid Cell Pooling strategy and pushed the changes to the feat/grid-cell-pooling branch.

Implementation Highlights:

Dynamic Pool Sizing: Neo.grid.Body now auto-scales the cell pool based on the visible column range, preventing ID collisions.

Stable VDOM Structure: Neo.grid.Row renders the full cell pool (active cells + hidden placeholders) in a strict index-based order. This guarantees O(1) DOM stability with zero insertNode, removeNode, or moveNode operations during scrolling, as confirmed by the latest delta logs.

Plain Object Safety: Added robust fallback logic in Row.applyRendererOutput to support lazy-loaded (plain object) records correctly.

Hybrid Mode: Permanent cells (e.g. Sparklines) are preserved outside the pool to maintain their state/context.

Verification: The latest logs confirm that horizontal scrolling now generates purely attribute updates (innerHTML, style, cls), achieving the performance goal.

Branch: feat/grid-cell-pooling Next Steps: Review and merge the PR.

tobiu assigned to @tobiu on Feb 4, 2026, 11:44 PM

tobiu Feb 4, 2026, 11:45 PM

Input from Gemini 3 Pro:

✦ I have verified the performance gains with real-world scrolling data from the Big Data Grid example (50 rows, 10 columns visible).

Performance Analysis:

Scroll Operation: Full horizontal scroll (Left to Right).

Total Frames: 12 frames.

Total Deltas: ~3250 attribute updates.

Operations: Strictly updateNode (innerHTML, style). Zero insertNode or moveNode operations were observed during the scroll phase.

This confirms that the Stable VDOM Sorting strategy successfully eliminated the massive layout thrashing caused by node rotation, and the Cell Pooling strategy successfully eliminated the GC overhead of node destruction. The result is a highly efficient, O(1) virtual scrolling implementation.

Task Complete. Closing ticket.

tobiu closed this issue on Feb 4, 2026, 11:49 PM