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	9226
title	Enhance KB: Document maxUsers cap and performance trade-offs in DevIndex
state	Closed
labels	documentationai
assignees	tobiu
createdAt	Feb 21, 2026, 3:21 PM
updatedAt	Feb 21, 2026, 3:22 PM
githubUrl	https://github.com/neomjs/neo/issues/9226
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 21, 2026, 3:22 PM

Enhance KB: Document maxUsers cap and performance trade-offs in DevIndex

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

Closed v12.0.0 documentationai

tobiu commented on Feb 21, 2026, 3:21 PM

Following the implementation of the maxUsers cap (50k limit) for the DevIndex, we need to apply the Knowledge Base Enhancement Strategy to document this architectural decision.

Rationale: If we allowed the index to grow unbounded (e.g., 100k users), the users.jsonl file would reach ~40MB. While we stream and gzip the data, client-side memory constraints and parsing overhead would eventually degrade the application's responsiveness and UX. The cap ensures the app remains fast and "fun to use" while maintaining high quality via the dynamic contribution threshold.

Tasks:

Update Storage.mjs: Enhance the class-level JSDoc to explain the pruning mechanism and the performance trade-off rationale behind the users.jsonl file size.
Update config.mjs: Add detailed context to the maxUsers property explaining why the 50,000 limit exists (40MB file size, client-side performance).
Update Updater.mjs: Briefly mention the dynamic threshold interaction with the maxUsers cap in the workflow description.

tobiu added the documentation label on Feb 21, 2026, 3:21 PM

tobiu added the ai label on Feb 21, 2026, 3:21 PM

tobiu referenced in commit a64625e - "docs(devindex): Enhance KB by documenting maxUsers cap and performance trade-offs (#9226)" on Feb 21, 2026, 3:22 PM

tobiu assigned to @tobiu on Feb 21, 2026, 3:22 PM

tobiu Feb 21, 2026, 3:22 PM

Input from Gemini 3 Pro:

✦ I have applied the Knowledge Base Enhancement Strategy to document the new 50k user cap and its architectural rationale.

config.mjs: Added a detailed explanation to the maxUsers property, highlighting the ~40MB file size projection for 100k users and the client-side memory/parsing trade-offs.

Storage.mjs: Expanded the class-level @summary to document the maxUsers cap, explaining how it protects the UI responsiveness by enforcing a capped users.jsonl size and raising the threshold.json bar.

Updater.mjs: Enhanced the class-level workflow documentation to clarify how the "Filter" phase utilizes the dynamic threshold managed by Storage once the cap is reached.

These changes are committed and pushed to dev. Closing the issue.

tobiu closed this issue on Feb 21, 2026, 3:22 PM