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	8164
title	Enhance Neo.manager.Window to Track Full Window Geometry
state	Closed
labels	enhancementaiarchitecture
assignees	tobiu
createdAt	Dec 27, 2025, 10:30 PM
updatedAt	Dec 28, 2025, 12:53 AM
githubUrl	https://github.com/neomjs/neo/issues/8164
author	tobiu
commentsCount	1
parentIssue	8163
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 28, 2025, 12:53 AM

Enhance Neo.manager.Window to Track Full Window Geometry

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

Closed v11.18.0 enhancementaiarchitecture

tobiu commented on Dec 27, 2025, 10:30 PM

During the implementation of cross-window drag & drop, we discovered that Neo.manager.Window primarily tracked the outer window rect (screen coordinates of the frame). To correctly position elements inside the viewport (like the drag proxy), we patched it to calculate headerHeight (outerHeight - innerHeight).

Issue: The current Window model is incomplete. It confounds "Screen Position" (Frame) with "Content Position" (Viewport). This leads to ad-hoc calculations in consumers like DragCoordinator to infer the browser chrome size.

Goal: Refactor Neo.manager.Window to explicitly track and expose:

outerRect: The window frame on the OS screen.
innerRect (or viewportRect): The content area on the OS screen.
chromeDimensions: Top/Left/Right/Bottom border sizes.

Benefits:

Simplifies cross-window positioning (popups, proxies, infinite canvas).
Enables precise "center on parent content" logic.
Removes fragile headerHeight assumptions.

tobiu added the enhancement label on Dec 27, 2025, 10:30 PM

tobiu added the ai label on Dec 27, 2025, 10:30 PM

tobiu added the architecture label on Dec 27, 2025, 10:30 PM

tobiu added parent issue #8163 on Dec 27, 2025, 10:33 PM

tobiu assigned to @tobiu on Dec 28, 2025, 12:00 AM

tobiu referenced in commit 146980c - "Neo.manager.Window: Implement full window geometry tracking with Cross-Browser Viewport Support - #8164 on Dec 28, 2025, 12:52 AM

tobiu Dec 28, 2025, 12:53 AM

Input from gemini:

✦ I have implemented the enhanced window geometry tracking to support the "Infinite Canvas" across different browsers.

Key Changes:

Refactored Neo.manager.Window:

Added calculateGeometry to interpret raw window data and derive innerRect (viewport), outerRect (frame), and chrome dimensions.

Implemented browser-specific logic:

Firefox: Uses mozInnerScreenX/Y directly for precise viewport positioning.

Safari: Uses isSafari flag (cached via navigator.userAgent) to correct for the frame-based screenLeft/Top coordinates by adding calculated chrome.

Chrome/Edge: Uses screenLeft/Top as the viewport origin (standard behavior).

Updated onWindowConnect and onWindowPositionChange to use this robust logic.

Updated Neo.manager.DragCoordinator:

Switched from manual, brittle coordinate calculations to using the new targetWindow.innerRect. This ensures drop targets are detected exactly where the user sees them, regardless of browser chrome size.

Updated Neo.Main:

Modified getWindowData to report raw sensor data, including mozInnerScreenX/Y. It now acts as a dumb sensor, delegating interpretation to the Worker.

Reverted Neo.main.addon.WindowPosition:

Restored to its simpler state of tracking raw screenLeft/Top for movement detection, maintaining clean separation of concerns.

This foundation allows precise cross-window coordinate mapping for all major browsers.

tobiu closed this issue on Dec 28, 2025, 12:53 AM