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	8723
title	ServicesCanvas: Upgrade ''Runners'' to ''Neural Agents''
state	Closed
labels	enhancementdesignai
assignees	tobiu
createdAt	Jan 16, 2026, 7:07 PM
updatedAt	Jan 16, 2026, 8:07 PM
githubUrl	https://github.com/neomjs/neo/issues/8723
author	tobiu
commentsCount	1
parentIssue	8721
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 16, 2026, 8:07 PM

ServicesCanvas: Upgrade 'Runners' to 'Neural Agents'

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

Closed v11.23.0 enhancementdesignai

tobiu commented on Jan 16, 2026, 7:07 PM

Context: Currently, ServicesCanvas.mjs features "Runners"—dots that zip along the grid lines blindly. They represent simple data packets or network traffic.

Goal: Upgrade these entities to represent "Neural Agents" that actively maintain and inspect the runtime.

Requirements:

Agency: Agents should not just move; they should act.
Scanning Behavior: When an Agent reaches a node (random chance or deterministic), it should:
- Stop or slow down significantly.
- Trigger a "Scan" animation (e.g., expanding ring or color pulse).
- Change the state of the node (e.g., permanently change its color to "Optimized" or boost its energy).
Visuals: Give them a distinct visual signature (e.g., a "Head" with a "Tail", similar to HomeCanvas, but adapted for the Hex grid).
Zero-Allocation: Ensure this new behavior maintains the strict zero-allocation policy (use pre-allocated buffers).

tobiu added the enhancement label on Jan 16, 2026, 7:07 PM

tobiu added the design label on Jan 16, 2026, 7:07 PM

tobiu added the ai label on Jan 16, 2026, 7:07 PM

tobiu added parent issue #8721 on Jan 16, 2026, 7:07 PM

tobiu referenced in commit 44fdd75 - "feat: Upgrade Runners to Neural Agents with stateful Scanning behavior (#8723)" on Jan 16, 2026, 8:06 PM

tobiu Jan 16, 2026, 8:06 PM

Input from Gemini 3 Pro:

✦ I have upgraded the Runners to Neural Agents with the following changes:

Stateful Behavior: Agents now implement a Moving/Scanning state machine.

Agency: Agents have a 20% chance to stop and "Scan" a node upon arrival.

Visuals:

Head: Agents now have a distinct Diamond-shaped head.

Action: Scanning triggers a Radar Pulse and Vertical Beam.

Theme Awareness: The Agent Head adapts to the theme (White in Dark Mode, Neo Blue in Light Mode) to ensure visibility, fixing the concern about white-on-white.

Logic: A successful scan instantly boosts the node's BuildCharge by +5, guaranteeing a Super Hex trigger. This ensures visual cause-and-effect.

Zero-Allocation: RUNNER_STRIDE was increased to 10 to store state and timers in the buffer.

The task is complete.

tobiu cross-referenced by #8721 on Jan 16, 2026, 8:07 PM

tobiu assigned to @tobiu on Jan 16, 2026, 8:07 PM

tobiu closed this issue on Jan 16, 2026, 8:07 PM