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	8690
title	Optimize ServiceWorker Update Transition
state	Closed
labels	enhancementaiperformancecore
assignees	tobiu
createdAt	Jan 15, 2026, 2:08 PM
updatedAt	Jan 15, 2026, 2:19 PM
githubUrl	https://github.com/neomjs/neo/issues/8690
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 15, 2026, 2:19 PM

Optimize ServiceWorker Update Transition

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

Closed v11.22.0 enhancementaiperformancecore

tobiu commented on Jan 15, 2026, 2:08 PM

Users report blank pages during Neo.mjs version updates. The investigation reveals that the current implementation of onActivate performs synchronous, blocking cache deletion inside event.waitUntil(). This prevents the browser from handling fetch events until all old caches are deleted, leading to perceived hang times or blank pages.

Changes:

Refactor onActivate to perform clients.claim() immediately and resolve waitUntil.
Move cache cleanup logic to a dedicated cleanUpCaches method.
Trigger cleanUpCaches asynchronously (fire-and-forget) after activation, ensuring the UI thread is not blocked during the update.

tobiu added the enhancement label on Jan 15, 2026, 2:08 PM

tobiu added the ai label on Jan 15, 2026, 2:08 PM

tobiu added the performance label on Jan 15, 2026, 2:08 PM

tobiu added the core label on Jan 15, 2026, 2:08 PM

tobiu referenced in commit 398b508 - "enhancement: Optimize ServiceWorker update transition (#8690)" on Jan 15, 2026, 2:18 PM

tobiu Jan 15, 2026, 2:19 PM

Input from Gemini 3 Pro:

✦ I have optimized the ServiceWorker update transition to prevent blocking page loads.

Changes Implemented:

Lazy Cache Cleanup: The onActivate handler now triggers cleanUpCaches() asynchronously without awaiting it inside event.waitUntil(). This ensures the Service Worker activates and claims clients immediately.

Dedicated Cleanup Method: Added cleanUpCaches() to ServiceBase.mjs to handle the iteration and deletion of old versioned caches.

Verification of Versioning: Confirmed that ServiceBase relies on this.cacheName (which appends this.version) to isolate caches per version (e.g., neo-runtime-11.21.0).

Impact:

Faster Updates: The new Service Worker will take control of the page almost instantly after installation.

No Blocking: The deletion of old caches (which can be slow) happens in the background, allowing network requests for the new version to proceed immediately.

Blank Page Fix: This should resolve the reported issue where users saw a blank page while the SW was busy deleting old files.

The changes have been pushed to dev.

tobiu assigned to @tobiu on Jan 15, 2026, 2:19 PM

tobiu closed this issue on Jan 15, 2026, 2:19 PM