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	8923
title	Refactor: Optimize Neural Link get_component_tree for token efficiency
state	Closed
labels	enhancementaiperformance
assignees	tobiu
createdAt	Jan 31, 2026, 4:01 PM
updatedAt	Jan 31, 2026, 5:22 PM
githubUrl	https://github.com/neomjs/neo/issues/8923
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 31, 2026, 5:22 PM

Refactor: Optimize Neural Link get_component_tree for token efficiency

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

Closed v12.0.0 enhancementaiperformance

tobiu commented on Jan 31, 2026, 4:01 PM

The get_component_tree tool currently returns full component serialization (including VDOM, VNode, listeners) for every node in the hierarchy, resulting in massive payloads (1M+ tokens) for complex apps.

Goals:

Introduce a lean mode (default: true) to ComponentService.getComponentTree.
Strict Whitelisting: In lean mode, return only the following properties: id, className, ntype, parentId, items.
Ensure the recursion logic respects this whitelist, preventing any other configs (like vdom, vnode, listeners, theme, style) from leaking into the output.

Impact: Reduce payload size by ~95%, enabling agents to inspect large application trees without exhausting context windows.

tobiu added the enhancement label on Jan 31, 2026, 4:01 PM

tobiu added the ai label on Jan 31, 2026, 4:01 PM

tobiu added the performance label on Jan 31, 2026, 4:01 PM

tobiu assigned to @tobiu on Jan 31, 2026, 5:12 PM

tobiu referenced in commit c1be3ba - "refactor: Optimize Neural Link get_component_tree for token efficiency (#8923) on Jan 31, 2026, 5:20 PM

tobiu Jan 31, 2026, 5:21 PM

Input from Gemini 3 Pro:

✦ I have implemented the 'lean' mode for get_component_tree.

Changes:

Strict Whitelisting: In lean mode (which defaults to true), the serialization now only includes:

id

className

items (recursive)

Removal of Redundancy: I removed ntype and parentId from the lean output as discussed, as they are either redundant (implied by hierarchy) or can be derived from className.

Schema Update: Updated openapi.yaml to include the lean parameter definition and description.

This should drastically reduce the token count for component tree inspections.

tobiu closed this issue on Jan 31, 2026, 5:22 PM