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	7903
title	Refactor Knowledge Base crawling logic into Source Providers
state	Closed
labels	airefactoring
assignees	tobiu
createdAt	Nov 25, 2025, 4:44 PM
updatedAt	Nov 25, 2025, 5:16 PM
githubUrl	https://github.com/neomjs/neo/issues/7903
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 25, 2025, 5:16 PM

Refactor Knowledge Base crawling logic into Source Providers

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

Closed v11.11.0 airefactoring

tobiu commented on Nov 25, 2025, 4:44 PM

Goal: Further decouple DatabaseService.mjs by extracting the crawling and iteration logic into dedicated Source classes. This respects the Single Responsibility Principle: DatabaseService should manage the DB, while Sources should know how to find and extract content.

Architecture:

Create a new namespace Neo.ai.mcp.server.knowledge-base.source.
File Location: ai/mcp/server/knowledge-base/source/ (Sibling to services/ and parser/).
Each Source class should be a Neo.core.Base singleton.

New Classes:

source/Base.mjs: Abstract base class defining the extract(writeStream) contract.
source/ApiSource.mjs: Handles docs/output/all.json iteration -> Uses ApiParser.
source/LearningSource.mjs: Handles learn/tree.json and learn/ traversal -> Uses DocumentationParser.
source/ReleaseNotesSource.mjs: Handles .github/RELEASE_NOTES scanning.
source/TicketSource.mjs: Handles .github/ISSUE_ARCHIVE scanning.
source/TestSource.mjs: Handles test/playwright scanning -> Uses TestParser.

Impact: DatabaseService.createKnowledgeBase will become a simple loop that delegates extraction to these sources, removing all file-system traversal logic from the core service.

tobiu added the ai label on Nov 25, 2025, 4:44 PM

tobiu added the refactoring label on Nov 25, 2025, 4:44 PM

tobiu assigned to @tobiu on Nov 25, 2025, 4:44 PM

tobiu referenced in commit 9dd9549 - "Refactor Knowledge Base crawling logic into Source Providers #7903" on Nov 25, 2025, 5:13 PM

tobiu Nov 25, 2025, 5:14 PM

Input from Neo Agent:

◆ I have successfully implemented the refactoring of the Knowledge Base parsing and crawling logic.

Verification Results:

Architecture: The system now uses dedicated Parser and Source singletons, decoupling content extraction from the DatabaseService.

Parsing: Playwright tests are correctly decomposed into granular chunks with line number metadata.

Crawling: The new Source classes (ApiSource, LearningSource, etc.) correctly iterate their respective domains.

Sync: A full manual database synchronization was performed, confirming that the new architecture correctly rebuilds the ai-knowledge-base.jsonl file and updates ChromaDB (7448 chunks).

The codebase is now significantly cleaner, adhering to SRP and better prepared for future content types.

tobiu closed this issue on Nov 25, 2025, 5:16 PM