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	8016
title	Harden Neural Link MCP Server
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 3, 2025, 11:17 PM
updatedAt	Dec 28, 2025, 7:37 PM
githubUrl	https://github.com/neomjs/neo/issues/8016
author	tobiu
commentsCount	2
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 28, 2025, 7:37 PM

Harden Neural Link MCP Server

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

Closed v11.18.0 enhancementai

tobiu commented on Dec 3, 2025, 11:17 PM

The Neural Link MCP Server requires hardening to match the standards set by memory-core.

Requirements:

HealthService: Implement HealthService.mjs to monitor WebSocket server and ConnectionService status.
Server Enhancements: Update Server.mjs to perform health checks during tool calls and startup.
Logging: Add detailed startup and error logging.
OpenAPI: Ensure openapi.yaml correctly defines all tools and is used for validation.

Acceptance Criteria:

Server reports health status on startup.
Tools fail gracefully if the server is unhealthy.
All tools are validated against OpenAPI specs.

tobiu added the enhancement label on Dec 3, 2025, 11:17 PM

tobiu added the ai label on Dec 3, 2025, 11:17 PM

tobiu Dec 3, 2025, 11:22 PM

Input from Antigravity:

◆ Clarification on Acceptance Criteria:

The requirement "Server reports health status on startup" signifies that the server must output clear debugging logs to the console indicating its health status (e.g., "Neural Link MCP Server started", "Health Check Passed"). It does not imply a proactive push to the client unless the client explicitly requests a health check.

tobiu added parent issue #8169 on Dec 28, 2025, 2:39 PM

tobiu assigned to @tobiu on Dec 28, 2025, 7:18 PM

tobiu Dec 28, 2025, 7:37 PM

Input from Gemini 3.0:

✦ I have completed the hardening of the Neural Link MCP Server.

Summary of Changes:

Health Service: Implemented HealthService.mjs to monitor the WebSocket server and active connections, mirroring the memory-core architecture.

Server Lifecycle: Updated Server.mjs to perform health checks on startup and gate tool execution (except for healthcheck) based on server health.

Connection Monitoring: Enhanced ConnectionService.mjs with a getStatus() method to expose session and window counts.

OpenAPI Specs: Significantly enhanced openapi.yaml with:

A new /health endpoint.

Detailed "When to Use" descriptions for all tools.

Logical tagging and improved schema definitions.

Tool Registration: Registered the healthcheck tool in toolService.mjs.

The server now reports its health status on startup and provides a robust foundation for the upcoming Neural Link capabilities.

tobiu closed this issue on Dec 28, 2025, 7:37 PM

tobiu referenced in commit 7663897 - "feat(ai): Harden Neural Link MCP Server (#8016) on Dec 28, 2025, 7:53 PM