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	7945
title	Refactor: MCP Client Lifecycle and CLI Runner Renaming
state	Closed
labels	airefactoring
assignees	tobiu
createdAt	Nov 30, 2025, 1:50 AM
updatedAt	Nov 30, 2025, 2:13 AM
githubUrl	https://github.com/neomjs/neo/issues/7945
author	tobiu
commentsCount	1
parentIssue	7931
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 30, 2025, 2:13 AM

Refactor: MCP Client Lifecycle and CLI Runner Renaming

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

Closed v11.14.0 airefactoring

tobiu commented on Nov 30, 2025, 1:50 AM

Refactor the MCP Client architecture to ensure clear separation of concerns, consistent lifecycle management, and appropriate naming.

Deliverables

Refactor Neo.ai.mcp.client.Client (ai/mcp/client/Client.mjs):
- Lifecycle: Move connection logic from connect() to initAsync(). The client should self-connect during initialization. connect() should be removed or made private.
- Configuration: Add configFile config. Inside initAsync, call ClientConfig.load(this.configFile) if provided, before resolving server details.
- Proxies: Ensure dynamic tool proxies (this.tools) are created during initAsync.
Rename and Refactor CLI Runner:
- Rename: Move ai/mcp/client/mcp-stdio.mjs to ai/mcp/client/mcp-cli.mjs.
- Logic: Update the script to use the new Client lifecycle (await Neo.create(Client, ...).ready()).
- Implementation: Keep the CLI logic (argument parsing, executing client.listTools() or client.tools.x(), logging results) inside this runner script.
- Cleanup: Ensure client.close() is called before exit.
Update package.json:
- Update ai:mcp-client script to point to ai/mcp/client/mcp-cli.mjs.
Refactor Neo.ai.Agent (ai/Agent.mjs):
- Remove the connect() method.
- Move client creation, client.ready() calls, and tool aggregation logic into Agent.initAsync().
- The Agent itself will then be ready when its initAsync completes.
Update ai/agents/mcp-demo-agent.mjs:
- Refactor to use await agent.ready() instead of await agent.connect().
- Verify compatibility.

tobiu assigned to @tobiu on Nov 30, 2025, 1:50 AM

tobiu added the ai label on Nov 30, 2025, 1:50 AM

tobiu added the refactoring label on Nov 30, 2025, 1:50 AM

tobiu added parent issue #7931 on Nov 30, 2025, 1:50 AM

tobiu referenced in commit c541ee2 - "Refactor: MCP Client Lifecycle and CLI Runner Renaming #7945" on Nov 30, 2025, 2:12 AM

tobiu Nov 30, 2025, 2:12 AM

Input from Gemini 2.5:

✦ I have completed the refactoring to align the MCP Client Lifecycle and rename the CLI runner.

Deliverables Completed

Refactor Neo.ai.mcp.client.Client (ai/mcp/client/Client.mjs):

Moved connection logic from the connect() method into initAsync().

Removed the connect() method entirely.

Added configFile config and integrated config loading into initAsync().

The client now correctly self-connects and ensures readiness when await client.ready() is called.

Rename and Refactor CLI Runner:

Renamed ai/mcp/client/mcp-stdio.mjs to ai/mcp/client/mcp-cli.mjs.

Updated the runner script to use the new Client lifecycle (await Neo.create(Client, ...).ready()).

The runner now correctly executes CLI actions and closes the client.

Update package.json:

Modified the ai:mcp-client NPM script to point to ai/mcp/client/mcp-cli.mjs.

Refactor Neo.ai.Agent (ai/Agent.mjs):

Removed the connect() method.

Moved client creation, client.ready() calls, and tool aggregation logic into Agent.initAsync().

Ensured this.clients is correctly populated.

Update ai/agents/mcp-demo-agent.mjs:

Refactored to use await agent.ready() instead of await agent.connect().

Verified all client and agent interactions.

This refactoring ensures architectural consistency across the client and server components and aligns the lifecycle management with Neo.core.Base principles.

tobiu closed this issue on Nov 30, 2025, 2:13 AM