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	8878
title	Restructure Testing Documentation (Phase 1: Component & Unit Guides)
state	Closed
labels	documentationai
assignees	[]
createdAt	Jan 26, 2026, 11:03 AM
updatedAt	Jan 26, 2026, 11:17 AM
githubUrl	https://github.com/neomjs/neo/issues/8878
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 26, 2026, 11:17 AM

Restructure Testing Documentation (Phase 1: Component & Unit Guides)

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

Closed v11.24.0 documentationai

tobiu commented on Jan 26, 2026, 11:03 AM

Restructure the testing documentation to clearly separate Unit Testing from Component Testing.

Tasks:

Create learn/guides/testing/ComponentTesting.md:
- Document the "Real Browser" testing strategy using the empty-viewport app.
- Explain the neo fixture API (test/playwright/fixtures.mjs) for creating/manipulating components.
- Explain the single-worker constraint.
Rename & Update learn/guides/testing/Playwright.md:
- Rename to learn/guides/testing/UnitTesting.md.
- Update content to explicitly focus on the Node.js/Single-Thread simulation aspect.
Update learn/tree.json:
- Reflect the new file names and structure.

Goal: Provide clear, distinct entry points for the two testing methodologies.

tobiu added the documentation label on Jan 26, 2026, 11:03 AM

tobiu added the ai label on Jan 26, 2026, 11:03 AM

tobiu referenced in commit ba4bae1 - "docs: Restructure testing guides (#8878)" on Jan 26, 2026, 11:16 AM

tobiu Jan 26, 2026, 11:16 AM

Input from Gemini 3 Pro:

✦ I have completed the first phase of the testing documentation restructuring.

Changes:

Renamed: learn/guides/testing/Playwright.md -> learn/guides/testing/UnitTesting.md.

Updated the content to explicitly focus on the single-thread Node.js simulation mode.

Created: learn/guides/testing/ComponentTesting.md.

Documented the browser-based testing architecture using the empty-viewport app.

Detailed the usage of the neo fixture for interacting with components.

Explained the single-worker constraint.

Updated: learn/tree.json to reflect the new structure.

The testing documentation now has distinct entry points for Unit and Component testing.

tobiu closed this issue on Jan 26, 2026, 11:17 AM