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	8963
title	Feat: Smooth Data Transitions for Sparklines
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Feb 3, 2026, 2:01 PM
updatedAt	Feb 3, 2026, 2:29 PM
githubUrl	https://github.com/neomjs/neo/issues/8963
author	tobiu
commentsCount	1
parentIssue	8930
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 3, 2026, 2:29 PM

Feat: Smooth Data Transitions for Sparklines

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

Closed v12.0.0 enhancementai

tobiu commented on Feb 3, 2026, 2:01 PM

Currently, when the data array for a Sparkline changes, the chart snaps instantly to the new shape.

Task: Implement a smooth transition animation (approx. 200ms - 300ms) when the values array is updated. The chart points should interpolate from their old positions to the new ones.

Details:

Handle the transition in the Worker renderer (src/canvas/Sparkline.mjs).
Ensure the animation is performant and interrupts gracefully if new data arrives during a transition.
Consider how this interacts with the "Pulse" animation (it should probably pause or blend).

tobiu added the enhancement label on Feb 3, 2026, 2:01 PM

tobiu added the ai label on Feb 3, 2026, 2:01 PM

tobiu added parent issue #8930 on Feb 3, 2026, 2:01 PM

tobiu referenced in commit 331d58f - "Feat: Smooth Data Transitions for Sparklines (#8963)" on Feb 3, 2026, 2:26 PM

tobiu Feb 3, 2026, 2:29 PM

Input from Gemini 3 Pro:

✦ I have implemented smooth data transition animations for Neo.canvas.Sparkline.

Changes:

src/component/Sparkline.mjs: Added useTransition_ config (default: true). This allows developers to toggle the animation on/off.

src/canvas/Sparkline.mjs:

Updated renderLoop to handle value interpolation using a Cubic Ease-Out curve.

Updated updateData to initialize the transition if useTransition is enabled.

Ensured instantaneous updates for initial loads or when useTransition is false.

Outcome: When the values array of a Sparkline component updates, the chart points now glide smoothly to their new positions over 300ms, instead of snapping instantly. This creates a more polished, "living" data visualization experience.

tobiu assigned to @tobiu on Feb 3, 2026, 2:29 PM

tobiu closed this issue on Feb 3, 2026, 2:29 PM