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	9132
title	Implement 'Network Walker' Discovery Strategy (Social Graph)
state	Closed
labels	enhancementaifeature
assignees	tobiu
createdAt	Feb 13, 2026, 2:39 AM
updatedAt	Feb 13, 2026, 2:42 AM
githubUrl	https://github.com/neomjs/neo/issues/9132
author	tobiu
commentsCount	1
parentIssue	9106
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 13, 2026, 2:42 AM

Implement 'Network Walker' Discovery Strategy (Social Graph)

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

Closed v12.0.0 enhancementaifeature

tobiu commented on Feb 13, 2026, 2:39 AM

We have reached 15k users and want to expand our discovery beyond repository-based searches. Developers often follow other skilled developers. Traversing this "Social Graph" is a high-probability way to find "hidden gems"—active developers who might not have high-star repositories but are followed by other productive engineers.

New Strategy: "Network Walker" (User-to-User)

Selection: Pick a random user from our existing index who has a high contribution count (e.g., > 1000). High performers tend to follow other high performers.
Traversal: Fetch the list of users they follow (GET /users/:username/following).
Discovery:
- Filter out users already in tracker.json or blacklist.json.
- Add new discoveries to tracker.json as pending.

Implementation:

Modify apps/devindex/services/Spider.mjs.
Add runNetworkWalker method.
Integrate into the weighted strategy selection (pickStrategy).

tobiu added the enhancement label on Feb 13, 2026, 2:39 AM

tobiu added the ai label on Feb 13, 2026, 2:39 AM

tobiu added the feature label on Feb 13, 2026, 2:39 AM

tobiu assigned to @tobiu on Feb 13, 2026, 2:39 AM

tobiu added parent issue #9106 on Feb 13, 2026, 2:39 AM

tobiu referenced in commit 4af7e1d - "feat(devindex): Implement Network Walker discovery strategy (#9132)" on Feb 13, 2026, 2:41 AM

tobiu Feb 13, 2026, 2:41 AM

Input from Gemini 3 Pro:

✦ I have implemented the "Network Walker" discovery strategy.

Features:

New Strategy: network_walker added to pickStrategy with a ~15% weight.

Implementation: The runNetworkWalker method picks a random existing user and fetches their following list (up to 100 users).

Discovery: It filters out users who are already in the tracker.json or blacklist.json and adds the rest as pending candidates.

Integration: Fully integrated into the run loop and supports forced execution via CLI (though CLI flag support might need explicit args if not already string type).

This strategy will help discover high-quality "hidden gems" by traversing the social graph of existing high-value users.

tobiu closed this issue on Feb 13, 2026, 2:42 AM