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	7859
title	Documentation: Enhance "Code Execution with MCP" Guide
state	Closed
labels	documentationenhancementai
assignees	tobiu
createdAt	Nov 22, 2025, 5:44 PM
updatedAt	Nov 22, 2025, 5:59 PM
githubUrl	https://github.com/neomjs/neo/issues/7859
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 22, 2025, 5:59 PM

Documentation: Enhance "Code Execution with MCP" Guide

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

Closed v11.9.0 documentationenhancementai

tobiu commented on Nov 22, 2025, 5:44 PM

Objective: Enhance the "Code Execution with MCP" guide (learn/guides/mcp/CodeExecution.md) to provide a more comprehensive explanation of the "Thick Client" pattern, the Neo.mjs AI SDK, and the runtime type safety mechanisms.

Context: The current guide introduces the concept but lacks detailed explanations of the underlying mechanics (OpenAPI + Zod validation) and a step-by-step breakdown of the "Self-Healing" workflow. This update will align the documentation with the latest SDK capabilities and Anthropic's "Code Execution" patterns.

Tasks:

Update learn/guides/mcp/CodeExecution.md:
- Refine the "Concept" section to explicitly reference Anthropic's "Code Execution" pattern.
- Expand the "SDK" section to detail ai/services.mjs and its role as a bridge.
- Deep dive into "Runtime Type Safety," explaining how OpenApiValidator.mjs uses Zod and OpenAPI specs to protect the system.
- Walk through the ai/examples/self-healing.mjs script, explaining the "Monitor -> Understand -> Plan -> Act" loop.
Ensure learn/tree.json is up-to-date (it should already be, but verification is good).

Outcome: A definitive guide that empowers developers and agents to build autonomous workflows using the Neo.mjs AI SDK.

tobiu added the documentation label on Nov 22, 2025, 5:44 PM

tobiu added the enhancement label on Nov 22, 2025, 5:44 PM

tobiu added the ai label on Nov 22, 2025, 5:44 PM

tobiu assigned to @tobiu on Nov 22, 2025, 5:46 PM

tobiu referenced in commit e9bebad - "Documentation: Enhance "Code Execution with MCP" Guide #7859" on Nov 22, 2025, 5:59 PM

tobiu closed this issue on Nov 22, 2025, 5:59 PM

tobiu Nov 22, 2025, 5:59 PM

Input from Neo Agent:

◆ I have reviewed the final version of learn/guides/mcp/CodeExecution.md from a storytelling perspective.

Assessment: The guide effectively narrates the evolution of the "Agent OS" architecture:

The Hook: It opens by establishing "Code Execution" as the "pinnacle" of the architecture, creating immediate interest.

The Conflict: It vividly contrasts the "Old Way" (Chatty, Fragile, Slow) with the "New Way" (Autonomous, Fast, Efficient), clearly defining the problem.

The Mechanics: The "Services vs. Servers" and "Type Safety" sections provide the necessary "hard magic" explanation—showing how the system works without breaking the narrative flow.

The Climax: The "Self-Healing" example serves as the narrative peak, demonstrating the full power of the system in a real-world scenario.

The Resolution: The "When to Use" section provides a clear, actionable conclusion for the reader.

The addition of real output logs grounds the abstract concepts in reality, reinforcing the "developer-first" tone. The guide is now complete and ready for publication.