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	8719
title	Refactor ServicesCanvas.mjs for Zero-Allocation & Architecture
state	Closed
labels	airefactoringperformance
assignees	tobiu
createdAt	Jan 16, 2026, 6:40 PM
updatedAt	Jan 16, 2026, 6:43 PM
githubUrl	https://github.com/neomjs/neo/issues/8719
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 16, 2026, 6:43 PM

Refactor ServicesCanvas.mjs for Zero-Allocation & Architecture

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

Closed v11.23.0 airefactoringperformance

tobiu commented on Jan 16, 2026, 6:40 PM

The ServicesCanvas.mjs component requires a technical overhaul to align with the "Zero Allocations" paradigm and improve maintainability.

Goals:

Eliminate GC Pressure:
- Refactor getProjection to avoid creating closures and objects per frame.
- Refactor project() to write to a shared/reusable mutable object instead of returning new objects for every vertex.
- Optimize findNeighbors to avoid creating arrays in the render loop.
Architecture:
- Clean up method organization.
- Ensure strict Neo.mjs coding guidelines (comments, formatting).
Performance:
- Optimize math operations.

tobiu added the ai label on Jan 16, 2026, 6:40 PM

tobiu added the refactoring label on Jan 16, 2026, 6:40 PM

tobiu added the performance label on Jan 16, 2026, 6:40 PM

tobiu referenced in commit 4f4c30d - "refactor: Optimize ServicesCanvas for zero-allocation performance (#8719)" on Jan 16, 2026, 6:43 PM

tobiu assigned to @tobiu on Jan 16, 2026, 6:43 PM

tobiu Jan 16, 2026, 6:43 PM

Input from Gemini 3 Pro:

✦ I have completed the refactoring of ServicesCanvas.mjs.

Changes:

Zero Allocation Projection: Replaced getProjection (which created closures and objects per frame) with updateProjection and a reusable projectionPoint object.

Optimized Draw Methods: Updated drawHex, drawKernel, drawStrata, drawGraph, drawRunners, and drawDebris to use the new allocation-free project method.

Runner Gradients: Optimized drawRunners to reuse projection results, avoiding double-projection and preventing object creation.

The render loop now operates with significantly reduced GC pressure.

tobiu closed this issue on Jan 16, 2026, 6:43 PM