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	9229
title	Optimize Spider Core Strategy with Power-Law Distribution
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Feb 21, 2026, 3:42 PM
updatedAt	Feb 21, 2026, 3:45 PM
githubUrl	https://github.com/neomjs/neo/issues/9229
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 21, 2026, 3:45 PM

Optimize Spider Core Strategy with Power-Law Distribution

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

Closed v12.0.0 enhancementai

tobiu commented on Feb 21, 2026, 3:42 PM

The DevIndex Spider's "Core: High Stars" strategy currently uses a linear random distribution to select repository star ranges between minStars (1000) and 20,000.

Since GitHub repository star counts follow a steep power-law distribution (exponentially more repos exist in the 1k-5k range than the 15k-20k range), a linear random selection wastes API quota on high-star slices that contain few or no repositories.

Tasks:

Update apps/devindex/services/Spider.mjs to apply a power curve (e.g., Math.pow(Math.random(), 3)) to the random offset calculation in the pickStrategy method.
This mathematical tweak will skew the Spider's discovery efforts heavily toward the denser, lower-star ranges where the vast majority of undiscovered, high-quality repositories reside, significantly increasing discovery efficiency per API call.

tobiu added the enhancement label on Feb 21, 2026, 3:42 PM

tobiu added the ai label on Feb 21, 2026, 3:42 PM

tobiu referenced in commit 419fd00 - "feat(devindex): Optimize Spider Core strategy with power-law distribution (#9229)" on Feb 21, 2026, 3:44 PM

tobiu assigned to @tobiu on Feb 21, 2026, 3:44 PM

tobiu Feb 21, 2026, 3:44 PM

Input from Gemini 3 Pro:

✦ I have successfully implemented the power-law distribution for the Spider's Core strategy.

In apps/devindex/services/Spider.mjs, the randomOffset calculation was updated from: const randomOffset = Math.floor(Math.random() * 19000); to: const randomOffset = Math.floor(Math.pow(Math.random(), 3) * 19000);

This mathematical tweak ensures that 50% of the generated random slices fall within the lowest 12.5% of the high-star spectrum (i.e., minStars + 2375). This heavily weights the Spider's searches toward the denser ranges containing the vast majority of repositories (1000 - 3375 stars), yielding significantly more candidates per API call, while still allowing occasional deep-dives into the rarified 15,000+ star repos.

Changes have been pushed to dev. Closing the issue.

tobiu closed this issue on Feb 21, 2026, 3:45 PM