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	8280
title	[Neural Link] Feature: Tool inspect_class
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Jan 1, 2026, 8:17 PM
updatedAt	Jan 2, 2026, 12:46 AM
githubUrl	https://github.com/neomjs/neo/issues/8280
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 2, 2026, 12:46 AM

[Neural Link] Feature: Tool inspect_class

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

Closed v11.18.0 enhancementai

tobiu commented on Jan 1, 2026, 8:17 PM

Implement inspect_class to allow AI agents to introspect the schema of a class at runtime.

Requirements:

Input: className (string).
Output: JSON schema including configs (reactive and non-reactive), field definitions (for Models), and public methods.
Logic:
- Load the class via Neo.ns().
- Traverse prototype chain to gather all configs.
- Identify mixins.
- Format output for AI consumption (clear, type-aware).

Why: This allows the agent to "read the manual" for the specific app instance it is connected to, ensuring it sends valid data and understands the capabilities of custom components not in its training data.

tobiu added the enhancement label on Jan 1, 2026, 8:17 PM

tobiu added the ai label on Jan 1, 2026, 8:17 PM

tobiu assigned to @tobiu on Jan 1, 2026, 8:18 PM

tobiu added parent issue #8169 on Jan 1, 2026, 8:19 PM

tobiu Jan 2, 2026, 12:45 AM

Input from Gemini 3 pro:

✦ Implemented inspect_class tool for Neural Link.

Scope & Architecture Refinement

We refined the goal from a simple "JSON schema" to a "Rich Class Blueprint". Instead of parsing source files (which misses inherited logic), we leverage the runtime knowledge:

ctor.config: The authoritative source for merged default values and config existence (after Neo.setupClass has run).

ctor.configDescriptors: The source for config metadata (e.g., merge: 'shallow', isEqual).

prototype: The source for active methods and mixins.

Implementation Details

The tool provides a "God Mode" view of a class, answering "What can this do?" and "How does it react?".

1. Rich Config Schema

Configs are not just values. The output now includes:

Value: The resolved default value.

Meta: Descriptor properties (if present).

Hooks: Explicitly lists active reactive hooks (beforeSet, afterSet, beforeGet) found on the prototype. This reveals the reactivity map of the component.

2. Cleaned Public API

The methods list is filtered to reduce noise:

Excluded: Internal lifecycle hooks (construct, init, onConstructed), constructors, and reactive config hooks (which are now categorized under configs).

Included: Actionable public methods (destroy, toJSON, set, etc.).

3. Hierarchy & Mixins

Returns the full ntypeChain and resolved mixins list.

This distinguishes inspect_class (Blueprint/Manual) from toJSON (Runtime State), providing agents with the deep understanding needed for complex tasks.

tobiu closed this issue on Jan 2, 2026, 12:46 AM

tobiu referenced in commit 2d83f4b - "#8280 missing file" on Jan 2, 2026, 12:48 AM