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	9134
title	Fix Organization Leakage in DevIndex and Updater Retries
state	Closed
labels	bugai
assignees	tobiu
createdAt	Feb 13, 2026, 3:06 AM
updatedAt	Feb 13, 2026, 3:09 AM
githubUrl	https://github.com/neomjs/neo/issues/9134
author	tobiu
commentsCount	1
parentIssue	9106
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 13, 2026, 3:09 AM

Fix Organization Leakage in DevIndex and Updater Retries

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

Closed v12.0.0 bugai

tobiu commented on Feb 13, 2026, 3:06 AM

Organizations are leaking into the tracker.json index (e.g., loomnetwork), causing the Updater to waste cycles retrying queries that will never succeed.

Root Cause (Spider): The Network Walker (and potentially other strategies) fetches lists of users (e.g., following) but does not filter out entities where type === 'Organization'.

Symptom (Updater): When the Updater encounters these Orgs, GitHub.mjs misinterprets the "Could not resolve to a User" GraphQL error as a network error and retries it 3 times.

Tasks:

Spider.mjs: Update runNetworkWalker (and fetchContributors) to strictly filter for type: 'User'.
GitHub.mjs: Update error handling to Abort Retry immediately if the error contains "Could not resolve to a User" or "NOT_FOUND".

tobiu added the bug label on Feb 13, 2026, 3:06 AM

tobiu added the ai label on Feb 13, 2026, 3:06 AM

tobiu assigned to @tobiu on Feb 13, 2026, 3:06 AM

tobiu added parent issue #9106 on Feb 13, 2026, 3:06 AM

tobiu referenced in commit a0b60fc - "fix(devindex): Fix Organization leakage and prevent retry on 404s (#9134)" on Feb 13, 2026, 3:08 AM

tobiu Feb 13, 2026, 3:08 AM

Input from Gemini 3 Pro:

✦ I have implemented the fixes to prevent Organization leakage and stop wasteful retries.

Changes:

Spider (Spider.mjs): Updated runNetworkWalker to strictly filter for user.type === 'User'. This prevents Organizations (like loomnetwork) from being added to the tracker when walking the social graph.

GitHub Service (GitHub.mjs):

Updated the if (json.errors) block to check for "Could not resolve to a User" or "NOT_FOUND".

If found, it throws a GraphQL Fatal Error immediately, bypassing the retry logic.

Updated the catch block to explicitly re-throw these fatal errors, ensuring they don't get caught by the generic network retry handler.

This ensures that the DevIndex remains focused on developers and handles invalid entities gracefully without burning API quota on retries.

tobiu closed this issue on Feb 13, 2026, 3:09 AM