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	9386
title	E2E: Add min velocity threshold to Grid Predictive Scrolling
state	Closed
labels	aiperformancegrid
assignees	tobiu
createdAt	Mar 7, 2026, 11:44 PM
updatedAt	Mar 7, 2026, 11:47 PM
githubUrl	https://github.com/neomjs/neo/issues/9386
author	tobiu
commentsCount	1
parentIssue	9380
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Mar 7, 2026, 11:47 PM

E2E: Add min velocity threshold to Grid Predictive Scrolling

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

Closed v12.1.0 aiperformancegrid

tobiu commented on Mar 7, 2026, 11:44 PM

This ticket tracks the implementation of a minimum velocity threshold for Predictive Delta Injection in ScrollManager.

Goal: Fix the "jumpy" and "flickering" rendering behavior during low-velocity scrolling (e.g., mousewheel).

Tasks:

Update syncGridBody to require a minimum scrollVelocity (e.g., > 0.5 px/ms) before applying the kinematic prediction math.
For velocities below the threshold, fall back to rendering the exact, actual scrollTop.

This ensures that prediction only engages during deliberate, fast thumb drags where the worker pipeline lag actually causes a visible gap, preserving 1:1 pixel accuracy for precise scrolling.

This is a sub-task of the Epic to resolve Grid Scroll Thrashing.

tobiu added the ai label on Mar 7, 2026, 11:44 PM

tobiu added the performance label on Mar 7, 2026, 11:44 PM

tobiu added the grid label on Mar 7, 2026, 11:44 PM

tobiu added parent issue #9380 on Mar 7, 2026, 11:44 PM

tobiu referenced in commit 7e62b15 - "fix: Add min velocity threshold to Grid Predictive Scrolling (#9386) on Mar 7, 2026, 11:46 PM

tobiu assigned to @tobiu on Mar 7, 2026, 11:46 PM

tobiu Mar 7, 2026, 11:46 PM

Input from Gemini 3.1 Pro:

✦ I have implemented the minimum velocity threshold in ScrollManager.

The kinematic prediction math now only engages if Math.abs(scrollVelocity) > 0.5. For low-velocity scrolling (like a typical mousewheel tick), the Grid simply renders the exact, real-time scrollTop of the native container. This completely eliminates the decoupling effect and fixes the "jumpy/flickering" visual regression for precise scroll movements.

Closing this ticket as complete. We can now proceed with extracting E2E benchmark logs or tackling the directional buffer expansion for massive thumb jumps.

tobiu closed this issue on Mar 7, 2026, 11:47 PM