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	8674
title	Implement Agent-Driven State
state	Closed
labels	enhancementaiperformance
assignees	tobiu
createdAt	Jan 15, 2026, 3:39 AM
updatedAt	Jan 15, 2026, 4:04 AM
githubUrl	https://github.com/neomjs/neo/issues/8674
author	tobiu
commentsCount	2
parentIssue	8661
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 15, 2026, 4:04 AM

Implement Agent-Driven State

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

Closed v11.22.0 enhancementaiperformance

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

Objective

Visualize the Agent OS controlling the runtime. Agents shouldn't just be observers; they should affect the system.

Tasks

Energy Transfer: When an Agent "scans" (hovers) a node, increment an energy value on that node.
Visual Feedback: High energy nodes should glow brighter, grow larger, or spin faster.
Decay: Node energy should slowly decay over time, creating a "heat map" of recent agent activity.

Technical Details

Add energy field to nodeBuffer (update NODE_STRIDE).
Update drawNetwork to use energy for color/size modulation.

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 2bbf7f7 - "feat: Implement Agent-Driven State for Neural Swarm (#8674)" on Jan 15, 2026, 3:59 AM

tobiu Jan 15, 2026, 4:00 AM

Input from Gemini 3 Pro:

✦ I have implemented Agent-Driven State.

Changes:

State Model: Added energy field (0.0 - 1.0) to nodeBuffer (index 8).

Agent Interaction: When an Agent "scans" a node (arrives at target), it energizes it (sets energy = 1.0).

Physics: Energy decays by 1% per frame (*= 0.99), creating a fading trail effect.

Visuals: High-energy nodes glow bright Cyan/White and increase in size, creating a "heat map" of agent activity that fades over time.

This visually connects the Agents to the Topology: the Agents are no longer just floating over the graph; they are interacting with it.

tobiu Jan 15, 2026, 4:03 AM

Input from Gemini 3 Pro:

✦ I have fixed the SyntaxError in updateAgents. A previous replace operation accidentally truncated the else block for the seeking behavior, leaving an unclosed brace. This has been restored.

The application should now load without the Unexpected token 'else' error.

tobiu closed this issue on Jan 15, 2026, 4:04 AM