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	8352
title	Docs: Refine README Vocabulary to ''Engine Subsystems'' & ''Scene Graph''
state	Closed
labels	documentationenhancementairefactoring
assignees	tobiu
createdAt	Jan 6, 2026, 12:42 PM
updatedAt	Jan 7, 2026, 11:19 PM
githubUrl	https://github.com/neomjs/neo/issues/8352
author	tobiu
commentsCount	3
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 7, 2026, 11:19 PM

Docs: Refine README Vocabulary to 'Engine Subsystems' & 'Scene Graph'

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

Closed v11.19.0 documentationenhancementairefactoring

tobiu commented on Jan 6, 2026, 12:42 PM

Execute the final phase of the "Application Engine" rebranding by shifting the technical vocabulary in README.md from "Web Framework" terms to "Systems Engineering" terms.

Specific Actions based on Strategic Feedback:

The "Why AI Loves Engines" Connection:
- Explicitly state that AI agents are blind in compiled frameworks because code != runtime.
- Explain that in Neo.mjs, the runtime object graph is the source of truth (Map = Territory), enabling perfect introspection.
Reframe "Features" as "Subsystems":
- "True Multithreading" -> "The Threading Subsystem" (App/Data/VDOM Workers).
- "Asymmetric VDOM" -> "The Rendering Pipeline" (Compressed JSON deltas).
Scene Graph Terminology:
- Update the "Batteries Included / Lego Technic" section to explicitly use the term "Scene Graph" to describe the hierarchy of persistent nodes.
Show Mutation:
- Enhance the code example section to show a standard class definition followed by a Runtime Mutation snippet (e.g., Neo.get('id').set(...)) to prove the engine capability.
Copy Tweaks:
- Rename "Code Execution (Thick Client)" -> "The Agent Runtime".
- Refine "F1 vs Toyota" analogy if a stronger one fits (e.g., "Flight Simulator vs Website Builder"), or strictly align it with the Engine narrative.

Goal: Ensure the vocabulary matches the title. An Engine has subsystems, pipelines, and a scene graph; a Framework has features and components.

tobiu added the documentation label on Jan 6, 2026, 12:42 PM

tobiu added the enhancement label on Jan 6, 2026, 12:42 PM

tobiu added the ai label on Jan 6, 2026, 12:42 PM

tobiu added the refactoring label on Jan 6, 2026, 12:42 PM

tobiu assigned to @tobiu on Jan 6, 2026, 12:43 PM

tobiu Jan 6, 2026, 12:44 PM

Input from Gemini 3 Pro:

✦ I will now execute the vocabulary refinement plan.

Step-by-Step:

AI Visibility: Update the "AI-Native" section to explain why the Engine architecture enables AI vision (Object Permanence vs Compilation).

Subsystems: Rename the "Key Features" headers to "Engine Subsystems" (Threading, Rendering Pipeline).

Scene Graph: Inject "Scene Graph" terminology into the "Batteries Included" section.

Mutation Example: Update the code example to show Neo.get().set() runtime mutation.

Refinements: Rename "Thick Client" to "Agent Runtime".

I will apply these changes sequentially to ensuring phrasing is precise.

tobiu Jan 6, 2026, 12:48 PM

Input from Gemini 3 Pro:

✦ I have executed the vocabulary refinement plan.

Changes applied:

Agent Runtime: Renamed "Thick Client" and added the "Map = Territory" explanation for why AI loves Engines.

Engine Subsystems: Renamed "Key Features" and restructured it to focus on "The Threading Subsystem", "The Rendering Pipeline", and "The Scene Graph".

Scene Graph: Updated the "Batteries Included" header to emphasize "The Scene Graph" over just Lego Technic.

Runtime Mutation: Added the Neo.get().set() code snippet to the example section.

The README.md now speaks the language of an Application Engine consistently throughout the document. I am ready to close this ticket.

tobiu referenced in commit 10ac75b - "Docs: Refine README vocabulary to Engine terms #8352" on Jan 6, 2026, 1:08 PM

tobiu referenced in commit 335f7cc - "Docs: Refine README vocabulary to Engine terms #8352" on Jan 6, 2026, 1:08 PM

tobiu Jan 6, 2026, 1:08 PM

Input from Gemini 3 Pro:

✦ I have successfully executed the final polish pass on README.md using granular replacements.

Changes applied:

AI Visibility: Verified the "Game Character" analogy and "suite of dedicated MCP servers" phrasing were already present (handled in previous step, confirmed via read_file).

Object Model: Renamed "Batteries Included" to "The Object Model: The Scene Graph".

Subsystems: Renamed "Clean Architecture" to "The Logic Subsystem" and "No npm Dependency Hell" to "The Module System".

Code Example: Verified the "No build step. No reload." comment was already present (handled in previous step, confirmed via read_file).

The README.md is now fully aligned with the "Application Engine" strategic identity. I am ready to close this ticket.

tobiu closed this issue on Jan 7, 2026, 11:19 PM