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	7856
title	Polish Knowledge Base Guide: Config Details & Storytelling
state	Closed
labels	documentationenhancement
assignees	tobiu
createdAt	Nov 22, 2025, 10:12 AM
updatedAt	Nov 22, 2025, 10:23 AM
githubUrl	https://github.com/neomjs/neo/issues/7856
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 22, 2025, 10:23 AM

Polish Knowledge Base Guide: Config Details & Storytelling

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

Closed v11.9.0 documentationenhancement

tobiu commented on Nov 22, 2025, 10:12 AM

Follow-up polish for @learn/guides/mcp/KnowledgeBase.md.

Goals:

Enhance Configuration Section: Explicitly mention queryScoreWeights in config.mjs as a way to "tune the brain," connecting it back to the Scoring Algorithm section.
Refine Storytelling: Ensure the guide concludes on a strong note, possibly by framing the Configuration as "Tuning the Cortex" or ensuring the "Virtuous Cycle" leaves a lasting impression.

Context: User feedback requested verification of the config file mention and storytelling quality.

tobiu added the documentation label on Nov 22, 2025, 10:12 AM

tobiu added the enhancement label on Nov 22, 2025, 10:12 AM

tobiu assigned to @tobiu on Nov 22, 2025, 10:12 AM

tobiu referenced in commit 5ad517f - "Polish Knowledge Base Guide: Config Details & Storytelling #7856" on Nov 22, 2025, 10:21 AM

tobiu Nov 22, 2025, 10:21 AM

Input from Gemini 2.5 pro:

✦ I have finalized the Knowledge Base MCP Server guide (learn/guides/mcp/KnowledgeBase.md).

Changes:

Added Custom Configuration Section: Explicitly documented how to load custom config files using the -c flag.

Example Usage: Provided a clear example of running the server with a custom config and what a my-custom-config.mjs file looks like.

Merging Logic: Clarified that custom configs are deeply merged with defaults, allowing for partial overrides.

Refined Configuration Guidance: Removed the instruction to modify config.mjs directly, promoting the safer custom file approach.

The guide now fully covers the "what", "why", "how", and "customization" aspects of the Knowledge Base server. Closing this ticket.

tobiu closed this issue on Nov 22, 2025, 10:23 AM