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	9453
title	Implement Pipeline IPC and Remote Execution Routing
state	Closed
labels	enhancementaiarchitecturecore
assignees	tobiu
createdAt	Mar 12, 2026, 7:23 PM
updatedAt	Mar 24, 2026, 9:12 PM
githubUrl	https://github.com/neomjs/neo/issues/9453
author	tobiu
commentsCount	1
parentIssue	9449
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Mar 24, 2026, 9:12 PM

Implement Pipeline IPC and Remote Execution Routing

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

Closed v12.1.0 enhancementaiarchitecturecore

tobiu commented on Mar 12, 2026, 7:23 PM

Goal

Enable the App Worker's Pipeline instance to seamlessly execute its counterpart inside the Data Worker.

Context

In issue #9451, we created Neo.data.Pipeline which handles instantiating a mirror of itself in the Data Worker if workerExecution: 'data' is set. However, calling pipeline.read() currently does nothing remotely. We need to implement the IPC messaging that triggers the remote execution.

Acceptance Criteria

Implement read(), create(), update(), and destroy() methods on Neo.data.Pipeline.
When invoked in the App Worker with workerExecution: 'data', these methods must send an IPC message (e.g., { action: 'pipeline.execute', id: this.remoteId, operation: 'read', params: ... }) to the Data Worker.
Add an onPipelineExecute message handler in src/worker/Data.mjs.
This handler must look up the correct Pipeline instance from this.instances, invoke the requested operation (which will run the local Connection, Parser, and Normalizer in the Data Worker), and then send the finalized record array back to the App Worker's Promise resolver.

tobiu added the enhancement label on Mar 12, 2026, 7:23 PM

tobiu added the ai label on Mar 12, 2026, 7:23 PM

tobiu added the architecture label on Mar 12, 2026, 7:23 PM

tobiu added the core label on Mar 12, 2026, 7:23 PM

tobiu added parent issue #9449 on Mar 12, 2026, 7:23 PM

tobiu cross-referenced by #9449 on Mar 12, 2026, 7:24 PM

tobiu assigned to @tobiu on Mar 12, 2026, 7:25 PM

tobiu changed title from Wire Data Worker Normalizer Execution Pipeline to Implement Pipeline IPC and Remote Execution Routing on Mar 12, 2026, 10:03 PM

tobiu cross-referenced by #9451 on Mar 12, 2026, 10:14 PM

tobiu cross-referenced by #9543 on Mar 24, 2026, 5:07 PM

tobiu referenced in commit 2b9b44b - "feat(data): implement Pipeline IPC and remote execution routing (#9453)" on Mar 24, 2026, 9:09 PM

tobiu Mar 24, 2026, 9:09 PM

Input from Gemini 3.1 Pro:

✦ I have implemented the Pipeline IPC and remote execution routing, leveraging the new Instance-to-Instance RemoteMethodAccess (RMA) layer we built in #9544.

Implementation Details:

Pipeline Operations (src/data/Pipeline.mjs):

Updated read() to use Neo.currentWorker.generateRemote to create a proxy to its Data Worker counterpart.

Implemented create() and update() methods using a shared executeRemoteOrLocal helper. This helper ensures that if workerExecution: 'data' is set, all operations are seamlessly routed via RMA to the remoteId.

Data Worker Cleanup (src/worker/Data.mjs):

Removed the Hack: Deleted the hardcoded onPipelineExecute message handler. The Data Worker no longer needs domain-specific logic to route Pipeline calls; the core RMA mixin handles it automatically via remoteId.

Memory Management: Added an onDestroyInstance handler. When the App Worker Pipeline is destroyed, it sends a destroyInstance message. This new handler ensures the remote instance is properly destroyed (instance.destroy()) and removed from the Data Worker's this.instances cache, preventing memory leaks.

The pipeline architecture is now fully wired for cross-worker orchestration. I will close this sub-issue.

tobiu closed this issue on Mar 24, 2026, 9:12 PM

tobiu cross-referenced by #9546 on Mar 24, 2026, 9:19 PM