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	7467
title	`ai:query` fails to find content in existing blog post
state	Closed
labels	bughelp wantedgood first issuehacktoberfestai
assignees	harikrishna-au
createdAt	Oct 12, 2025, 1:08 PM
updatedAt	Oct 23, 2025, 12:52 AM
githubUrl	https://github.com/neomjs/neo/issues/7467
author	tobiu
commentsCount	3
parentIssue	7296
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Oct 13, 2025, 11:34 AM

`ai:query` fails to find content in existing blog post

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

Closed v11.0.0 bughelp wantedgood first issuehacktoberfestai

tobiu commented on Oct 12, 2025, 1:08 PM

The npm run ai:query command is failing to find content that is confirmed to exist in a file within the /learn/blog/ directory. This failure occurs both in general searches and when specifically filtering with -t blog. This points to a potential bug in the knowledge base indexing process (createKnowledgeBase.mjs or embedKnowledgeBase.mjs) or the query filtering logic (queryKnowledgeBase.mjs).

Contributor Guidance

This ticket is a good candidate for Hacktoberfest. To solve this, you must use the project's "AI-Native" workflow. This involves using an AI agent (like Gemini CLI) to help you diagnose and fix the issue.

Please read the following guides before starting:

The agent will help you explore the relevant files (createKnowledgeBase.mjs, embedKnowledgeBase.mjs, queryKnowledgeBase.mjs), understand the code, and formulate a fix.

Steps to Reproduce

Verify that the file /Users/Shared/github/neomjs/neo/learn/blog/ai-native-platform-answers-questions.md contains the word "Tron".
Run the command: npm run ai:query -- -q "Tron" -t blog

Observed Behavior

The query returns the message: "No results found for your query and type."

Expected Behavior

The query should return /Users/Shared/github/neomjs/neo/learn/blog/ai-native-platform-answers-questions.md as a relevant result.

Impact

This bug severely reduces the reliability of the AI knowledge base. It can lead to confusing and incorrect agent interactions, as the agent is unable to find information that is known to exist in the project. This undermines the core "Anti-Hallucination Policy" defined in AGENTS.md.

Initial Analysis

The queryKnowledgeBase.mjs script contains the following filter logic:

case 'blog':
    return source.includes('/learn/blog/');

Given that the file path matches

tobiu added the bug label on Oct 12, 2025, 1:08 PM

tobiu added parent issue #7296 on Oct 12, 2025, 1:08 PM

tobiu added the help wanted label on Oct 12, 2025, 1:08 PM

tobiu added the good first issue label on Oct 12, 2025, 1:08 PM

tobiu added the hacktoberfest label on Oct 12, 2025, 1:08 PM

tobiu added the ai label on Oct 12, 2025, 1:08 PM

SarthakBorude Oct 12, 2025, 8:58 PM

hey i am a beginner and i would love to give it a try

2025-10-13T01:53:00Z @harikrishna-au referenced in commit 2107d69 - "Fix AI query blog filtering issue #7467
Blog content is stored as type:'guide' with isBlog:true
Query filter was incorrectly looking for type:'blog'
Updated queryKnowledgeBase.mjs to handle blog type correctly
Blog queries now filter for type:'guide' AND isBlog:'true'
Resolves AI knowledge base blog content access issue"
2025-10-13T01:54:33Z @harikrishna-au cross-referenced by PR #7472

@harikrishna-au - 2025-10-13T02:01:45Z

Hi @tobiu, apologies for not asking to be assigned to this issue beforehand. I’ve submitted a PR with the fix. Please have a look and let me know if any changes are needed. Thank you!

tobiu referenced in commit 39032f4 - "Fix AI query blog filtering issue #7467 on Oct 13, 2025, 10:39 AM

tobiu Oct 13, 2025, 11:34 AM

✦ Hi @harikrishna-au and @SarthakBorude, and thank you both for your engagement on this ticket.

First, thank you @harikrishna-au for the quick and effective PR. We have reviewed, approved, and merged it, and the bug is now resolved.

I want to take a moment to clarify our contribution workflow to ensure fairness and prevent duplicate work, especially during a busy time like Hacktoberfest. As a general guideline, please comment on an issue and wait for it to be assigned to you by a maintainer before you begin working. This helps us ensure that multiple people aren't unknowingly working on the same problem.

In this case, since a complete PR was already submitted, we made the practical decision to merge it. Asking someone to re-do work that is already complete would not be a good use of a contributor's valuable time.

@SarthakBorude, we really appreciate you volunteering for this. To ensure you have a great opportunity to contribute, we've created a follow-up ticket that addresses a related improvement we discovered during the review. We have created and reserved it specifically for you: #7474

Important: Due to GitHub's assignment policy, I can only assign the ticket to you after you've commented on it. Please leave a comment on the new issue (e.g., "Ready to start!") within the next 7 days, and I will officially assign it to you.

We're thrilled to have such high interest in the project and look forward to collaborating with all of you.

tobiu closed this issue on Oct 13, 2025, 11:34 AM

tobiu assigned to @harikrishna-au on Oct 13, 2025, 11:35 AM