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	9255
title	Create Backend ("Fat Client") Guide for DevIndex
state	Closed
labels	documentationenhancementai
assignees	tobiu
createdAt	Feb 22, 2026, 6:22 PM
updatedAt	Feb 22, 2026, 6:27 PM
githubUrl	https://github.com/neomjs/neo/issues/9255
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 22, 2026, 6:27 PM

Create Backend ("Fat Client") Guide for DevIndex

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

Closed v12.0.0 documentationenhancementai

tobiu commented on Feb 22, 2026, 6:22 PM

Objective: Replace the dummy "Architecture" guide in the DevIndex data factory learning path with a new "Backend" guide. This guide explains the "Fat Client" twist of the DevIndex application—specifically that it lacks a traditional backend server and instead relies on streaming a static users.jsonl file.

Tasks:

Create learn/guides/devindex/Backend.md.
Explain the "Fat Client" architecture and the pragmatic reasons for it (FOSS, GitHub Pages hosting limitations).
Describe the hyper-optimized NDJSON data format.
Explain the streaming architecture using Neo.data.proxy.Stream, ReadableStream, and progressiveChunkSize.
Document "Turbo Mode" (autoInitRecords: false) and "Soft Hydration" for memory-efficient sorting/filtering.
Detail the zero-overhead virtual fields feature using Neo.data.RecordFactory.
Update learn/guides/devindex/tree.json to link the new guide.

tobiu added the documentation label on Feb 22, 2026, 6:22 PM

tobiu added the enhancement label on Feb 22, 2026, 6:22 PM

tobiu added the ai label on Feb 22, 2026, 6:22 PM

tobiu assigned to @tobiu on Feb 22, 2026, 6:22 PM

tobiu referenced in commit 439689b - "docs: Create Backend guide and replace Architecture dummy (#9255)" on Feb 22, 2026, 6:27 PM

tobiu Feb 22, 2026, 6:27 PM

Input from Gemini 3 Pro:

✦ I have completed the creation of the Backend.md guide for DevIndex.

Key additions:

Explained the "Fat Client" architecture and how the users.jsonl file acts as the backend.

Detailed the pragmatic FOSS and GitHub Pages hosting constraints.

Documented the streaming architecture using Neo.data.proxy.Stream.

Clarified the "Turbo Mode" (autoInitRecords: false) for memory-efficient client-side sorting and filtering.

Highlighted the zero-overhead virtual fields feature using Neo.data.RecordFactory.

Updated tree.json to link the new guide and replace the "Architecture" dummy.

The changes have been successfully committed and pushed to the remote repository. Closing this issue.

tobiu closed this issue on Feb 22, 2026, 6:27 PM