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	7869
title	Refactor Memory Core MCP Server to use Neo.core.Base class architecture
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Nov 23, 2025, 10:32 AM
updatedAt	Nov 23, 2025, 11:14 AM
githubUrl	https://github.com/neomjs/neo/issues/7869
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 23, 2025, 11:14 AM

Refactor Memory Core MCP Server to use Neo.core.Base class architecture

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

Closed v11.9.0 enhancementai

tobiu commented on Nov 23, 2025, 10:32 AM

Objective: Refactor the Memory Core MCP server entry point to use a dedicated Neo.core.Base class for the server logic, replacing the procedural script approach. This unifies the architecture and leverages Neo.mjs lifecycle management (construct, initAsync, ready).

Changes:

Create ai/mcp/server/memory-core/Server.mjs:
- Define class Server extends Neo.core.Base.
- Do NOT make it a singleton. It should be a standard class.
- Config: Accept debug (Boolean) and configFile (String).
- construct(config):
  - Call super.construct(config).
  - Immediately sync aiConfig.data.debug if this.debug is true.
- initAsync():
  - Call super.initAsync().
  - Load custom config via aiConfig.load() if this.configFile is set.
  - Initialize McpServer instance.
  - Set up request handlers using listTools and callTool from services/toolService.mjs.
  - Await SessionService.ready().
  - Perform HealthService.healthcheck() and log status.
  - Initialize and connect StdioServerTransport.
- Methods: Extract helper methods for setupRequestHandlers and logStartupStatus for cleaner code.
Refactor ai/mcp/server/memory-core/mcp-stdio.mjs:
- Convert into a lightweight "runner" script.
- Use commander to parse CLI arguments (-d, -c).
- Instantiate the server: const server = Neo.create(Server, { ...options });
- Error Handling: Attach a catch handler to the ready promise:
```
        server.ready().catch(error => {
    logger.error('Fatal startup error:', error);
    process.exit(1);
});
```

Technical Details:

Ensures debug flag from CLI is respected immediately in the server constructor.
Uses server.ready() to bridge the gap between synchronous instantiation and asynchronous initialization errors.

tobiu assigned to @tobiu on Nov 23, 2025, 10:40 AM

tobiu added the enhancement label on Nov 23, 2025, 10:40 AM

tobiu added the ai label on Nov 23, 2025, 10:40 AM

tobiu referenced in commit 3f89302 - "Refactor Memory Core MCP Server to use Neo.core.Base class architecture #7869" on Nov 23, 2025, 11:11 AM

tobiu Nov 23, 2025, 11:14 AM

Input from Gemini:

✦ The implementation was adjusted during development to better align with the Neo.mjs architecture and Node.js best practices.

Final Implementation Details:

No Singleton: The Server class is a standard Neo.core.Base subclass, not a singleton. The single instance is created manually by the runner script.

Runner Pattern: mcp-stdio.mjs acts as a lightweight runner. It handles CLI parsing, global config setup (aiConfig.debug), and instantiates the Server.

Modern Error Handling: Instead of chained .catch() blocks, we utilized top-level await (Node.js v22+ / ESM) wrapped in a single try/catch block to handle both synchronous construction errors and asynchronous initialization failures gracefully.

Simplified Configs: debug and configFile were removed from static config and treated as class fields or handled directly by the runner to reduce overhead and redundancy. aiConfig is updated directly by the runner before the server starts.

Import Order: Strictly enforced import order in mcp-stdio.mjs (Neo -> core -> InstanceManager -> Server) to ensure the framework namespace is fully populated before the server class is evaluated.

tobiu closed this issue on Nov 23, 2025, 11:14 AM