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	8212
title	Enhance Neural Link Health Check with detailed diagnostics
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 30, 2025, 10:46 AM
updatedAt	Dec 30, 2025, 11:13 AM
githubUrl	https://github.com/neomjs/neo/issues/8212
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 30, 2025, 11:13 AM

Enhance Neural Link Health Check with detailed diagnostics

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

Closed v11.18.0 enhancementai

tobiu commented on Dec 30, 2025, 10:46 AM

The current HealthService for neural-link provides a basic status. To improve diagnostics and align with the memory-core implementation, we need to enhance the health check response.

Goal: Update ai/mcp/server/neural-link/services/HealthService.mjs to return a more detailed health payload, including:

Bridge Connection: Status of the connection to the standalone Bridge process.
Bridge Process: Status of the Bridge process (if managed/spawned by the service).
Session Details: More granular info about connected Agents and Apps.
Startup Status: Information about the initialization sequence.

Tasks:

Enhance HealthService.mjs to return the enriched payload.
Update openapi.yaml (HealthCheckResponse schema) to match the new structure.
Ensure backward compatibility or clear error messaging for clients expecting the old format (though internal agents adapt quickly).

Reference: See ai/mcp/server/memory-core/services/HealthService.mjs for the target pattern.

tobiu added the enhancement label on Dec 30, 2025, 10:46 AM

tobiu added the ai label on Dec 30, 2025, 10:46 AM

tobiu added parent issue #8169 on Dec 30, 2025, 10:46 AM

tobiu assigned to @tobiu on Dec 30, 2025, 10:46 AM

tobiu referenced in commit d805d42 - "feat(ai): Enhance Neural Link Health Check diagnostics (#8212) on Dec 30, 2025, 10:47 AM

tobiu Dec 30, 2025, 10:47 AM

Input from Gemini:

✦ I have enhanced the HealthService and openapi.yaml to provide detailed diagnostics. The healthcheck tool now returns information about:

Bridge Connection: Whether the agent is connected to the Bridge process.

Session Stats: Number of active apps and windows.

Agent Identity: The unique Agent ID used for routing.

This completes ticket #8212.

tobiu closed this issue on Dec 30, 2025, 11:13 AM

tobiu cross-referenced by #8214 on Dec 30, 2025, 11:19 AM