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	7950
title	Refactor ToolService to Class-based Architecture
state	Closed
labels	enhancementairefactoring
assignees	tobiu
createdAt	Nov 30, 2025, 3:38 PM
updatedAt	Nov 30, 2025, 4:10 PM
githubUrl	https://github.com/neomjs/neo/issues/7950
author	tobiu
commentsCount	1
parentIssue	7931
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 30, 2025, 4:10 PM

Refactor ToolService to Class-based Architecture

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

Closed v11.14.0 enhancementairefactoring

tobiu commented on Nov 30, 2025, 3:38 PM

Context

In #7949, we moved toolService.mjs to a shared location to support client-side validation. However, the service remains a singleton module with module-level state (toolMapping). This prevents a single process (like an Agent) from initializing multiple internal server contexts (Zod schemas) simultaneously, as subsequent initializations overwrite the global state.

Goal

Refactor ai/mcp/toolService.mjs into a class-based Neo.ai.mcp.ToolService extending Neo.core.Base. This allows each Server or Client connection to maintain its own independent tool registry and validation context.

Requirements

Rename & Refactor: Rename ai/mcp/toolService.mjs to ai/mcp/ToolService.mjs. Convert it to export a ToolService class extending Neo.core.Base.
Configuration:
- openApiFilePath: Define as a non-reactive config (no trailing underscore) to allow prototype or instance-level overrides.
Class Fields:
- serviceMapping: Define as a class field.
- toolMapping & allToolsForListing: Define as instance properties (lazy-loaded state).
Server Update: Update all MCP Servers (github-workflow, knowledge-base, memory-core) to instantiate new ToolService({ serviceMapping, openApiFilePath }) (or similar config pattern) in their local service wrappers.
Client Update: Update Neo.ai.mcp.client.Client to:
- Instantiate a ToolService for each connection.
- Pass the openApiFilePath (retrieved from config) to the ToolService if available, enabling robust Zod validation for internal servers.

Deliverables

ai/mcp/ToolService.mjs (Class-based).
Updated Servers and Client using the new class.

tobiu added the enhancement label on Nov 30, 2025, 3:38 PM

tobiu added the ai label on Nov 30, 2025, 3:38 PM

tobiu added the refactoring label on Nov 30, 2025, 3:38 PM

tobiu added parent issue #7931 on Nov 30, 2025, 3:38 PM

tobiu assigned to @tobiu on Nov 30, 2025, 3:38 PM

tobiu referenced in commit 7284f44 - "Refactor ToolService to Class-based Architecture #7950" on Nov 30, 2025, 4:10 PM

tobiu Nov 30, 2025, 4:10 PM

Input from Gemini 2.5 pro:

✦ I have successfully completed the singleton-to-class refactoring for ToolService.

Refactoring Details

Class Architecture: ai/mcp/ToolService.mjs is now a class extending Neo.core.Base.

State (toolMapping, allToolsForListing) is instance-scoped.

Configuration (openApiFilePath) is handled via static config and construct.

Server Migration: All three MCP servers (github-workflow, knowledge-base, memory-core) now instantiate a new ToolService(...) in their respective services/toolService.mjs wrappers, ensuring isolation.

Client Migration: Neo.ai.mcp.client.Client now creates a private ToolService instance for each connection (initAsync). This enables the Client to maintain separate validation contexts (e.g., separate Zod schemas) for different internal servers within the same process.

Verification

The mcp-demo-agent.mjs runs successfully, confirming that:

Servers initialize correctly with the new class-based service.

The Client connects and executes tools (using the new class-based validation logic).

The architecture handles the multi-server setup without state pollution.

I am ready to close this ticket.

tobiu closed this issue on Nov 30, 2025, 4:10 PM