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	9546
title	Refactor Pipeline IPC to use Declarative Remote Configs (Instance Proxies)
state	Closed
labels	enhancementaiarchitecturecore
assignees	tobiu
createdAt	Mar 24, 2026, 9:19 PM
updatedAt	Mar 24, 2026, 9:34 PM
githubUrl	https://github.com/neomjs/neo/issues/9546
author	tobiu
commentsCount	1
parentIssue	9449
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Mar 24, 2026, 9:34 PM

Refactor Pipeline IPC to use Declarative Remote Configs (Instance Proxies)

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

Closed v12.1.0 enhancementaiarchitecturecore

tobiu commented on Mar 24, 2026, 9:19 PM

Goal

Refactor the Neo.data.Pipeline class to utilize the declarative remote configuration for instance-to-instance IPC, replacing the procedural on-the-fly proxy generation.

Context

In issue #9453, we implemented the initial IPC routing for pipelines by explicitly calling Neo.currentWorker.generateRemote inside the read, create, and update methods.

This approach is highly procedural and violates the elegant, declarative design patterns of the framework. Neo.mjs heavily relies on defining capabilities statically (e.g., static config = { remote: ... }) and letting the class system or mixins handle the wiring.

We need to adopt "Option C" (Explicit remote Namespace on Instances): Instead of generating the proxy dynamically on every call, the Pipeline should define its remote capabilities in its static config. The framework should then automatically populate a this.remote object on the instance with pre-bound proxy functions during construction.

Acceptance Criteria

Add remote: { data: ['create', 'read', 'update'] } to the static config of Neo.data.Pipeline.
Update the initRemote method in src/core/Base.mjs (or the RMA mixin) to properly handle remote configs for non-singleton instances. If a class is not a singleton, it should generate the proxies and attach them to a remote property on the instance, organized by destination (e.g., this.remote.data.read).
Refactor Neo.data.Pipeline to remove the manual generateRemote calls and instead invoke the pre-generated proxies via this.remote.data[operation]({ ...params, remoteId: this.remoteId }).
Ensure the unit tests for RemoteMethodAccess and StoreParser continue to pass with this declarative architecture.

tobiu added the enhancement label on Mar 24, 2026, 9:19 PM

tobiu added the ai label on Mar 24, 2026, 9:19 PM

tobiu added the architecture label on Mar 24, 2026, 9:19 PM

tobiu added the core label on Mar 24, 2026, 9:20 PM

tobiu added parent issue #9449 on Mar 24, 2026, 9:20 PM

tobiu referenced in commit 9e2ab8b - "feat(core): support declarative remote configs for instance IPC (#9546) on Mar 24, 2026, 9:31 PM

tobiu assigned to @tobiu on Mar 24, 2026, 9:31 PM

tobiu Mar 24, 2026, 9:31 PM

Input from Gemini 3.1 Pro:

✦ I have refactored the Pipeline IPC architecture to use declarative remote configs, adhering to the highest code quality standards of core.Base.

Implementation Details:

Removed the Procedural Hacks: The generateRemote calls inside read and executeRemoteOrLocal have been removed from Pipeline.mjs. The pipeline now simply declares static config = { remote: { data: ['create', 'read', 'update'] } }.

core.Base.initRemote Enhancement:

I modified initRemote() to correctly handle non-singleton classes.

If a class is not a singleton, it now dynamically generates a this.remote object containing pre-bound proxy functions during instance construction.

These instance-level proxies are designed to resolve this.remoteId at execution time, perfectly accommodating the asynchronous "Handshake" pattern where the target ID is populated after the remote thread instantiates the counterpart.

Strict Promise Resolution: The user rightly pointed out that Base.promiseRemotes(className, remote) was only being called for singletons, which risked leaving the #remotesReadyPromise hanging. With the new implementation, non-singletons don't need to await global registration (registerRemote), so the synchronous population of the this.remote object allows the lifecycle to continue without blocking.

Knowledge Base Enhancements: The comments inside initRemote have been thoroughly updated using the Knowledge Base Enhancement Strategy. They clearly articulate the intent, differentiating "Singleton Routing (Namespace-Driven)" from "Instance-to-Instance Routing (ID-Driven)", and documenting the "Handshake" resolution pattern for future context.

The pipeline now executes cleanly via this.remote.data[operation](params), restoring the elegant DX of the Neo.mjs framework. I will close this sub-issue.

tobiu referenced in commit f3e2743 - "feat(core): support declarative remote configs for instance IPC (#9546) on Mar 24, 2026, 9:33 PM

tobiu closed this issue on Mar 24, 2026, 9:34 PM