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	8833
title	Enhancement: Verify Sparse Leapfrog Merging and Pruning
state	Closed
labels	enhancementaitestingcore
assignees	tobiu
createdAt	Jan 20, 2026, 7:35 PM
updatedAt	Jan 20, 2026, 7:38 PM
githubUrl	https://github.com/neomjs/neo/issues/8833
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 20, 2026, 7:38 PM

Enhancement: Verify Sparse Leapfrog Merging and Pruning

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

Closed v11.23.0 enhancementaitestingcore

tobiu commented on Jan 20, 2026, 7:35 PM

To confirm the robustness of the new "Sparse Tree Generation" optimization (Ticket #8832), we need to enhance the "Leapfrog Merging" test scenario in AsymmetricMerging.spec.mjs.

Goals:

Replace -1 with 2: The Leapfrog test currently uses updateDepth: -1 (infinite). We must replace this with updateDepth: 2 to prove that the new "Bridge Path" logic correctly handles specific depth requirements without needing a full-tree blast.
Verify Pruning: Add a "Clean Uncle" (sibling of the Bridge Parent) to the test structure.
Assertion: Verify that the "Bridge Parent" is expanded (to reach the Grandchild) but the "Clean Uncle" is pruned (sent as a placeholder), proving the selectivity of the new system.

Tasks:

Modify test/playwright/unit/vdom/AsymmetricMerging.spec.mjs.
Update the "Leapfrog Merging" test case.
Inspect the resulting deltas or vdom structure to confirm pruning behavior.

tobiu added the enhancement label on Jan 20, 2026, 7:35 PM

tobiu added the ai label on Jan 20, 2026, 7:35 PM

tobiu added the testing label on Jan 20, 2026, 7:35 PM

tobiu added the core label on Jan 20, 2026, 7:35 PM

tobiu assigned to @tobiu on Jan 20, 2026, 7:35 PM

tobiu referenced in commit 58a0b1f - "test: Enhance Leapfrog Merging test to verify Sparse Tree Generation (#8833) on Jan 20, 2026, 7:38 PM

tobiu Jan 20, 2026, 7:38 PM

Input from Gemini 3 Pro:

✦ I have enhanced the "Leapfrog Merging" test case in AsymmetricMerging.spec.mjs.

Changes:

Updated Depth: Replaced updateDepth: -1 with updateDepth: 2. The test still passes, confirming that the new "Bridge Path" logic correctly identifies and expands the intermediate parent even with a specific depth.

Verify Pruning: Added a clean-uncle component to the Grandparent. The test asserts that while the Grandchild's update is merged, the clean-uncle is not present in the resulting deltas. This confirms that the VDOM payload remains sparse and only the necessary branches (bridges) are traversed.

Result: Both the positive case (Leapfrog merge success) and the negative case (Uncle pruning) are verified.

tobiu closed this issue on Jan 20, 2026, 7:38 PM