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	8576
title	Investigate 'requestAnimationFrame' violations (55ms+)
state	Closed
labels	bugaiperformance
assignees	tobiu
createdAt	Jan 12, 2026, 4:09 AM
updatedAt	Jan 12, 2026, 5:53 AM
githubUrl	https://github.com/neomjs/neo/issues/8576
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 12, 2026, 5:53 AM

Investigate 'requestAnimationFrame' violations (55ms+)

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

Closed v11.20.0 bugaiperformance

tobiu commented on Jan 12, 2026, 4:09 AM

Issue: Following recent core changes, the console is reporting [Violation] 'requestAnimationFrame' handler took 55ms. This indicates a regression in the main thread's rendering performance.

Goal:

Investigate src/Main.mjs and src/main/DeltaUpdates.mjs to identify bottlenecks.
Instrument the code with performance logging (console.time/timeEnd or performance.now()) to isolate the slow operations.
Analyze the logs to determine if the issue is in VDOM parsing, DOM patching, or message handling.

tobiu added the bug label on Jan 12, 2026, 4:09 AM

tobiu added the ai label on Jan 12, 2026, 4:09 AM

tobiu added the performance label on Jan 12, 2026, 4:09 AM

tobiu referenced in commit 36c5c40 - "perf(DeltaUpdates): Implement DocumentFragment batching for contiguous insertNode operations (#8576)" on Jan 12, 2026, 5:52 AM

tobiu Jan 12, 2026, 5:52 AM

Input from Gemini 3 Pro:

✦ I have implemented a Batching Strategy for insertNode operations in src/main/DeltaUpdates.mjs.

The Solution: Contiguous insertNode operations targeting the same parent are now grouped into a single DocumentFragment. This batch is built in a detached state and inserted into the live DOM in a single atomic operation.

Performance Impact:

Reduced Reflows: Instead of 300+ individual insertions triggering layout calculations, we now have 1 reflow per batch.

Stability: We experimented with "Time Slicing" (generators) but found that the overhead and complexity outweighed the benefits for the initial viewport render (which takes ~60ms synchronously). The "blank page" risk of async rendering was deemed too high.

Result: The "slow operation" warning for large lists (e.g., 300 items) is now contained to ~40ms, which is within acceptable limits for a synchronous main thread operation.

Status:

Time-slicing logic has been reverted.

Performance logging has been removed.

Batching logic is active and verified.

Ready for final review.

tobiu assigned to @tobiu on Jan 12, 2026, 5:53 AM

tobiu closed this issue on Jan 12, 2026, 5:53 AM