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	8672
title	Implement Cluster Drift (Flow Fields)
state	Closed
labels	enhancementaiperformance
assignees	tobiu
createdAt	Jan 15, 2026, 3:39 AM
updatedAt	Jan 15, 2026, 3:49 AM
githubUrl	https://github.com/neomjs/neo/issues/8672
author	tobiu
commentsCount	1
parentIssue	8661
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 15, 2026, 3:49 AM

Implement Cluster Drift (Flow Fields)

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

Closed v11.22.0 enhancementaiperformance

tobiu commented on Jan 15, 2026, 3:39 AM

Objective

Replace simple linear velocity/bounce for Parent nodes with organic Flow Field movement.

Tasks

Flow Field: Implement 2D Simplex Noise or Perlin Noise (or a simple sine-sum field) to generate a velocity vector field across the canvas.
Parent Movement: PARENT nodes (Cluster Centers) should sample this field to determine their velocity (vx, vy). This will make them drift in "currents".
Child Propagation: Since Children seek Parents, they will naturally form "tails" or swarms following these currents.

Technical Details

Can use a lightweight pseudo-noise function (no heavy library needed).
Update updatePhysics to apply flow vectors to Parents.

tobiu assigned to @tobiu on Jan 15, 2026, 3:39 AM

tobiu added the enhancement label on Jan 15, 2026, 3:39 AM

tobiu added the ai label on Jan 15, 2026, 3:39 AM

tobiu added the performance label on Jan 15, 2026, 3:39 AM

tobiu added parent issue #8661 on Jan 15, 2026, 3:39 AM

tobiu referenced in commit a809e84 - "feat: Implement Cluster Drift (Flow Fields) for Neural Swarm (#8672)" on Jan 15, 2026, 3:47 AM

tobiu Jan 15, 2026, 3:48 AM

Input from Gemini 3 Pro:

✦ I have implemented the Cluster Drift using Flow Fields.

Changes:

Flow Field: Replaced the random drift for PARENT nodes with a calculated Vector Field.

Algorithm: Uses a combined Sine/Cosine function based on spatial position (x, y) and time to generate organic, swirling currents.

Dynamics: Parent nodes now "swim" along these currents. Since Child nodes are physically attracted to Parents (Cohesion), the entire cluster moves as a fluid swarm rather than a static group.

The result is a more biological, "living system" movement pattern.

tobiu closed this issue on Jan 15, 2026, 3:49 AM