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	9375
title	Improve ScrollSync Lock Release Mechanism (rAF vs setTimeout)
state	Closed
labels	enhancementaiarchitecture
assignees	tobiu
createdAt	Mar 7, 2026, 5:54 PM
updatedAt	Mar 7, 2026, 5:57 PM
githubUrl	https://github.com/neomjs/neo/issues/9375
author	tobiu
commentsCount	1
parentIssue	9369
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Mar 7, 2026, 5:57 PM

Improve ScrollSync Lock Release Mechanism (rAF vs setTimeout)

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

Closed v12.1.0 enhancementaiarchitecture

tobiu commented on Mar 7, 2026, 5:54 PM

Part of Epic #9369

Currently, the granular lock (coordinatingNodes Set) in ScrollSync.mjs is released on the next requestAnimationFrame. However, GridDragScroll utilizes a continuous requestAnimationFrame loop for momentum scrolling. Because native DOM scroll events are asynchronous to the render pipeline, they might dispatch to the event queue after the lock is released on the next frame, defeating the gatekeeper and causing a ping-pong loop.

Investigate and implement a safer lock release mechanism (e.g., using setTimeout to push the release to the end of the macrotask queue) to ensure the lock remains held across continuous 16ms programmatic mutations until all resulting native scroll events have been flushed by the browser.

tobiu added the enhancement label on Mar 7, 2026, 5:54 PM

tobiu added the ai label on Mar 7, 2026, 5:54 PM

tobiu added the architecture label on Mar 7, 2026, 5:54 PM

tobiu added parent issue #9369 on Mar 7, 2026, 5:54 PM

tobiu referenced in commit 78ba094 - "fix(Grid): change ScrollSync lock release to use debounced setTimeout (#9375)" on Mar 7, 2026, 5:56 PM

tobiu Mar 7, 2026, 5:56 PM

Input from Gemini 3.1 Pro:

✦ I have updated the lock release mechanism in ScrollSync.mjs to use a debounced setTimeout (default 50ms) instead of requestAnimationFrame.

Why: requestAnimationFrame releases the lock on the very next render tick. However, native DOM scroll events are dispatched asynchronously. If GridDragScroll's momentum loop fires an update every 16ms, a native scroll event might arrive after the rAF tick has already released the lock, causing a false positive in the interceptor and triggering a feedback loop.

The Fix: By using a Map of node IDs to timeout IDs, the lockNode method now clears any existing timeout and sets a new 50ms timer. This guarantees that during a continuous momentum throw (which updates the DOM every 16ms), the lock remains firmly held the entire time. It only releases 50ms after the final momentum update has settled, providing plenty of time for all trailing native asynchronous scroll events to be safely ignored by the gatekeeper.

tobiu closed this issue on Mar 7, 2026, 5:57 PM

tobiu assigned to @tobiu on Mar 7, 2026, 5:57 PM