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	8943
title	Feat: Interactive Living Sparklines
state	Closed
labels	enhancementdesignai
assignees	tobiu
createdAt	Feb 2, 2026, 1:25 AM
updatedAt	Feb 2, 2026, 2:33 AM
githubUrl	https://github.com/neomjs/neo/issues/8943
author	tobiu
commentsCount	2
parentIssue	8930
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 2, 2026, 2:33 AM

Feat: Interactive Living Sparklines

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

Closed v12.0.0 enhancementdesignai

tobiu commented on Feb 2, 2026, 1:25 AM

Transform the static sparkline into an interactive, high-performance visualization using the Canvas Worker engine.

Objectives

Interaction: Implement a "Time Scanner" that tracks the mouse cursor across the canvas, snapping to the nearest data point (Year/Value).
Visualization: Render a dynamic "scanner line" and a "glowing intersection point" on hover.
Canvas Text: Render the value/year directly on the canvas (avoiding DOM tooltip overhead).
Theming: Implement a theme-aware color system (like TicketCanvas) to support future light/dark modes.
Performance: Ensure the loop is efficient (only rendering when needed or using shared resources).

Technical Approach

App Worker: Forward mousemove and mouseleave events from SparklineComponent to the worker.
Canvas Worker:
- Implement getPointAtX math to snap to the Bezier curve.
- Render the overlay (Scanner + Text) on top of the cached static chart.
- Use requestAnimationFrame only when interaction is active.
- Define a static colors map with light and dark palettes.

tobiu added the enhancement label on Feb 2, 2026, 1:25 AM

tobiu added the design label on Feb 2, 2026, 1:25 AM

tobiu added the ai label on Feb 2, 2026, 1:25 AM

tobiu added parent issue #8930 on Feb 2, 2026, 1:26 AM

tobiu referenced in commit f406eed - "feat: Interactive Living Sparklines with optimized theming and performance (#8943)" on Feb 2, 2026, 2:31 AM

tobiu Feb 2, 2026, 2:31 AM

Input from Gemini 3 Pro:

✦ I have implemented the Interactive Living Sparklines feature with advanced canvas engine capabilities.

Key Enhancements

Canvas Engine Refactoring:

Refactored SparklineComponent to use a Wrapper Pattern (div > canvas), ensuring robust layout and event handling.

Implemented a SharedWorker-based Render Loop in Sparkline.mjs with cached geometry and optimized paint cycles.

Added High-DPI (Retina) support by synchronizing devicePixelRatio from the main thread via Neo.config updates.

Interaction Design:

Time Scanner: A vertical laser line tracks the mouse cursor, snapping to the nearest data point.

Data Overlay: Displays the exact Year and Contribution Value on hover, rendered directly on the canvas for performance.

Smart Layout: Text alignment adjusts dynamically near edges to prevent clipping.

Visual Polish:

Smooth Curves: Replaced linear segments with quadratic Bezier curves.

Gradient Fill: Added a vertical gradient under the curve to add volume.

Theming: Implemented a colors map supporting light and dark modes with semantic color slots (textYear, textValue).

Markers: Added a subtle glowing end-point and removed distracting peak markers in the resting state.

Integration:

Updated GridContainer to use the new component.

Moved all static styles to SCSS (resources/scss/src/apps/devrank/GridContainer.scss).

Updated src/worker/Manager.mjs to detect and expose devicePixelRatio globally.

The result is a high-performance, interactive micro-chart that feels alive and responsive.

tobiu assigned to @tobiu on Feb 2, 2026, 2:31 AM

tobiu closed this issue on Feb 2, 2026, 2:33 AM

tobiu Feb 2, 2026, 2:33 AM

Input from Gemini 3 Pro:

✦ Important Release Note: This feature introduces a new global configuration property: Neo.config.devicePixelRatio. This is automatically populated in src/worker/Manager.mjs by reading window.devicePixelRatio and is synchronized across all worker threads. This enables pixel-perfect canvas rendering on high-DPI (Retina) displays within App and Canvas workers.