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	9042
title	Enhancement: Dynamic High Star Ranges for Spider
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Feb 7, 2026, 10:20 PM
updatedAt	Feb 7, 2026, 10:21 PM
githubUrl	https://github.com/neomjs/neo/issues/9042
author	tobiu
commentsCount	1
parentIssue	8930
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 7, 2026, 10:21 PM

Enhancement: Dynamic High Star Ranges for Spider

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

Closed v12.0.0 enhancementai

tobiu commented on Feb 7, 2026, 10:20 PM

Enhance the "Core: High Stars" strategy in the Spider to avoid repeatedly scanning the same top-level repositories.

Current Behavior: The strategy uses a fixed query stars:>1000 (or configured minStars). This always returns the same top repositories (React, Vue, etc.), which are likely already visited, resulting in wasted runs.

Goal: Implement "Deep Slicing" by using random star count ranges. This allows the Spider to "jump" into the middle of the dataset (e.g., repositories with 1200-1500 stars) and treat them as "Page 1" of a new search, effectively bypassing the 1000-result limit of GitHub search API and discovering repositories that would otherwise be on Page 50+.

Logic: Instead of stars:>1000:

Pick a random lower bound (e.g., 1000 + random(0..10000)).
Pick a random upper bound (e.g., lower + 1000).
Query stars:LOWER..UPPER.

tobiu added the enhancement label on Feb 7, 2026, 10:20 PM

tobiu added the ai label on Feb 7, 2026, 10:20 PM

tobiu added parent issue #8930 on Feb 7, 2026, 10:20 PM

tobiu assigned to @tobiu on Feb 7, 2026, 10:20 PM

tobiu referenced in commit 0e3bbb6 - "enhancement: Dynamic High Star Ranges for Spider (#9042)" on Feb 7, 2026, 10:21 PM

tobiu Feb 7, 2026, 10:21 PM

Input from Gemini 3 Pro:

✦ Enhanced the "Core: High Stars" strategy to use dynamic star ranges (Slicing).

Changes

Replaced the static query stars:>1000 with a dynamic range generator.

Logic:

Lower Bound: 1000 + random(0..19000)

Upper Bound: Lower + 1000 + random(0..2000)

Query: stars:LOWER..UPPER

Impact

This allows the spider to randomly "jump" into the middle of the repository list (e.g., repositories with 1500-2000 stars) and scan them as Page 1. This effectively bypasses the GitHub search API limit of 1000 results and prevents the spider from repeatedly scanning only the top 30 most popular repositories.

Code committed to dev branch.

tobiu closed this issue on Feb 7, 2026, 10:21 PM