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	8196
title	Refactor: Neural Link - Client-Side Service Architecture
state	Closed
labels	airefactoringarchitecture
assignees	tobiu
createdAt	Dec 29, 2025, 12:40 AM
updatedAt	Dec 29, 2025, 7:27 AM
githubUrl	https://github.com/neomjs/neo/issues/8196
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 29, 2025, 7:27 AM

Refactor: Neural Link - Client-Side Service Architecture

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

Closed v11.18.0 airefactoringarchitecture

tobiu commented on Dec 29, 2025, 12:40 AM

Context: As we add more Neural Link tools (inspect_store, get_record, query_component, etc.), the src/ai/Client.mjs file's handleRequest method is becoming a massive switch-statement monolith. This mirrors the early state of the server-side ConnectionService before we split it into domain-specific services (DataService, ComponentService, etc.).

Problem:

Maintenance Risk: A single file handling all domain logic (data, UI, navigation, inspection) is hard to read and maintain.
Scalability: Adding new tools increases the file size and complexity linearly.
Testing: Harder to unit test isolated functionality when it's all in one "god method".

Requirement: Refactor the client-side handling into a service-based architecture, similar to the server-side.

Proposed Architecture:

Neo.ai.client.Service (Base Class): Base class for client-side services.
Domain Services:
- Neo.ai.client.ComponentService: Handles query_component, get_component_tree, etc.
- Neo.ai.client.DataService: Handles inspect_store, get_record, list_stores.
- Neo.ai.client.RuntimeService: Handles reload_page, get_window_info.
Service Registry: Neo.ai.Client should delegate requests to these registered services based on the method name or a lookup map.

Goal: Ensure the client-side architecture remains clean and scalable as the Neural Link capabilities grow.

tobiu added the ai label on Dec 29, 2025, 12:40 AM

tobiu added the refactoring label on Dec 29, 2025, 12:40 AM

tobiu added the architecture label on Dec 29, 2025, 12:40 AM

tobiu assigned to @tobiu on Dec 29, 2025, 12:40 AM

tobiu added parent issue #8169 on Dec 29, 2025, 12:40 AM

tobiu referenced in commit 7035edd - "refactor(ai): Implement Service-Based Client Architecture (#8196) on Dec 29, 2025, 7:26 AM

tobiu Dec 29, 2025, 7:26 AM

Input from Neo Agent OS:

◆ I have successfully refactored the Neural Link Client into a service-based architecture.

Changes:

Architecture:

Replaced the monolithic handleRequest in Neo.ai.Client with a dispatcher.

Created src/ai/client/Service.mjs as the base class.

Created domain services: ComponentService, DataService, RuntimeService.

Standards Compliance:

Enforced camelCase for all service methods (e.g., queryComponent).

Implemented Neo.snakeToCamel() in the dispatcher to map incoming JSON-RPC methods (snake_case) to internal methods.

Scalability:

New tools can now be added by extending the appropriate service without touching the main Client file.

The refactoring is verified and committed.

tobiu closed this issue on Dec 29, 2025, 7:27 AM