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	8191
title	Feat: Neural Link - Global Config Management
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 28, 2025, 10:30 PM
updatedAt	Jan 4, 2026, 11:16 AM
githubUrl	https://github.com/neomjs/neo/issues/8191
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 4, 2026, 11:16 AM

Feat: Neural Link - Global Config Management

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

Closed v11.18.0 enhancementai

tobiu commented on Dec 28, 2025, 10:30 PM

Context: Neo.config controls framework-level behavior. While some configs are boot-time constants (e.g., useSharedWorkers, environment), others are runtime-mutable (e.g., themes, custom app flags). Agents need access to this system.

Scope:

Enhance RuntimeService:
- Add getNeoConfig(sessionId).
  - Implementation: Return Neo.config.
- Add setNeoConfig(sessionId, config).
  - Implementation: Call Neo.setGlobalConfig(config).
Tools:
- get_neo_config: Returns the Neo.config object.
- set_neo_config: Accepts a partial config object.
- Documentation: Explicitly warn that changing boot-time configs (workers, environment) at runtime may not work or could cause instability.

Goal: Enable runtime configuration management.

tobiu added the enhancement label on Dec 28, 2025, 10:30 PM

tobiu added the ai label on Dec 28, 2025, 10:30 PM

tobiu added parent issue #8169 on Dec 28, 2025, 10:30 PM

tobiu assigned to @tobiu on Jan 4, 2026, 10:45 AM

tobiu referenced in commit 7d9bdd7 - "Feat: Neural Link - Global Config Management #8191" on Jan 4, 2026, 11:15 AM

tobiu Jan 4, 2026, 11:16 AM

Input from Gemini 2.5 pro:

✦ I have successfully implemented the Global Config Management feature for the Neural Link, enabling runtime inspection and modification of Neo.config.

Enhanced Scope: Multi-Window Awareness

During implementation, we identified a critical need to distinguish between the shared global state and the initial boot configuration of individual windows. We enhanced the get_neo_config tool to support an optional windowId parameter:

Global Config (Default): Returns the current, merged Neo.config shared across the App Worker.

Window Boot Config: If windowId is provided, returns the specific configuration used to initialize that window (stored in Neo.windowConfigs), allowing agents to inspect the "origin story" of a specific view.

Affected Files

Client-Side:

src/ai/client/RuntimeService.mjs: Added getNeoConfig and setNeoConfig methods.

Server-Side:

ai/mcp/server/neural-link/services/RuntimeService.mjs: Added bridge methods to delegate config requests to the client.

ai/mcp/server/neural-link/services/toolService.mjs: Registered get_neo_config and set_neo_config tools.

ai/mcp/server/neural-link/openapi.yaml: Defined the new API endpoints and schemas, including safety warnings for runtime config changes.

Documentation Cleanup

We also performed a cleanup pass to ensure windowId is consistently typed as String (UUID) across all JSDocs and API definitions, correcting legacy Number/integer references.

tobiu closed this issue on Jan 4, 2026, 11:16 AM