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	8308
title	Neural Link: Implement atomic get_vdom_and_vnode tool
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Jan 4, 2026, 12:47 PM
updatedAt	Jan 4, 2026, 1:02 PM
githubUrl	https://github.com/neomjs/neo/issues/8308
author	tobiu
commentsCount	2
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 4, 2026, 1:02 PM

Neural Link: Implement atomic get_vdom_and_vnode tool

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

Closed v11.18.0 enhancementai

tobiu commented on Jan 4, 2026, 12:47 PM

We need a new tool to retrieve both the VDOM and VNode trees for a component in a single, atomic operation.

Context:

get_vdom_tree returns the next intended state (VDOM).
get_vnode_tree returns the current live DOM state (VNode).
get_component_tree returns the Neo.mjs component hierarchy (Class instances).

Problem: In high-frequency scenarios (e.g., 60fps), fetching VDOM and VNode via separate network calls can lead to race conditions where the returned trees correspond to different render frames. This mismatch makes debugging rendering issues (reconciliation bugs) impossible.

Requirements:

New Tool: get_vdom_vnode (or get_render_trees)
Atomic: Must fetch both trees synchronously from the same component instance in the App Worker.
Parameters: rootId (string), depth (number, default -1).
Output: { vdom: Object, vnode: Object }.

Implementation:

Client: src/ai/client/ComponentService.mjs -> getVdomAndVnode({rootId, depth}).
Server: Update openapi.yaml, toolService.mjs, and server/services/ComponentService.mjs.

tobiu added the enhancement label on Jan 4, 2026, 12:47 PM

tobiu added the ai label on Jan 4, 2026, 12:47 PM

tobiu assigned to @tobiu on Jan 4, 2026, 12:47 PM

tobiu added parent issue #8169 on Jan 4, 2026, 12:47 PM

tobiu referenced in commit 432bd94 - "Neural Link: Implement atomic get_vdom_and_vnode tool #8308" on Jan 4, 2026, 12:52 PM

tobiu Jan 4, 2026, 12:52 PM

Input from Gemini 3 pro:

✦ I have implemented the atomic get_vdom_vnode tool across the full stack.

Server Side:

OpenAPI: Added /component/vdom-vnode/get endpoint to openapi.yaml.

Service: Added getVdomAndVnode to ai/mcp/server/neural-link/services/ComponentService.mjs.

Tool Mapping: Mapped get_vdom_vnode to ComponentService.getVdomAndVnode in ai/mcp/server/neural-link/services/toolService.mjs.

Client Side:

Service: Added getVdomAndVnode to src/ai/client/ComponentService.mjs, which uses TreeBuilder to return both trees synchronously.

Client: The get_vdom_vnode prefix is implicitly handled by the existing get_vdom mapping in Client.mjs (since get_vdom_vnode starts with get_vdom), so strictly speaking, no change was required in Client.mjs's map, but I verified the routing logic covers it. Wait, get_vdom prefix matches get_vdom_tree but also get_vdom_vnode.

Verification: The prefix matching in Client.mjs is:
for (prefix in me.serviceMap) {
    if (method.startsWith(prefix)) { ... }
}
Since get_vdom is a prefix, get_vdom_vnode will match it and route to component service. This confirms correct routing without explicit addition, though explicit addition (or re-ordering) might be safer if we had conflicting prefixes. Given the current list, it is safe.

The atomic tool is now ready for use.

tobiu Jan 4, 2026, 1:02 PM

Input from Gemini 3 pro:

✦ I have refined the implementation:

Renaming: Renamed getVdomAndVnode to getVdomVnode in src/ai/client/ComponentService.mjs to match the RPC method name more closely and follow conventions.

Client Cleanup: Fixed duplicated keys in src/ai/Client.mjs serviceMap that were inadvertently introduced during previous edits, ensuring a clean registration of get_vdom_vnode.

Formatting: Ensured the code changes adhere to project formatting standards (no extra newlines).

The feature is now fully implemented and polished.

tobiu closed this issue on Jan 4, 2026, 1:02 PM