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	8309
title	Feat: Neural Link - Get Method Source
state	Closed
labels	enhancementaiarchitecture
assignees	tobiu
createdAt	Jan 4, 2026, 1:54 PM
updatedAt	Jan 4, 2026, 2:07 PM
githubUrl	https://github.com/neomjs/neo/issues/8309
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 4, 2026, 2:07 PM

Feat: Neural Link - Get Method Source

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

Closed v11.18.0 enhancementaiarchitecture

tobiu commented on Jan 4, 2026, 1:54 PM

Context: To safely hot-patch code (Issue #8190), agents need to read the current implementation of a method. This is critical for "read-modify-write" workflows and works across all environments (dev, dist/esm, prod) by retrieving the actual runtime source via Function.toString().

Scope:

Client (RuntimeService.mjs):
- Implement getMethodSource({className, methodName}).
- Logic: Neo.ns(className).prototype[methodName].toString().
Server (MCP):
- Expose get_method_source tool.
- Update OpenAPI definition.

Goal: Enable agents to see the code they are about to patch.

tobiu added the enhancement label on Jan 4, 2026, 1:54 PM

tobiu added the ai label on Jan 4, 2026, 1:54 PM

tobiu added the architecture label on Jan 4, 2026, 1:54 PM

tobiu added parent issue #8169 on Jan 4, 2026, 1:55 PM

tobiu assigned to @tobiu on Jan 4, 2026, 1:55 PM

tobiu referenced in commit e23f496 - "feat(ai): Implement Get Method Source & Refine Hot-Patching (#8309) on Jan 4, 2026, 2:05 PM

tobiu referenced in commit 206b172 - "feat(ai): Expose Get Method Source Tool (Remaining Files) (#8309) on Jan 4, 2026, 2:05 PM

tobiu Jan 4, 2026, 2:06 PM

Input from Gemini 3 pro:

✦ Implemented get_method_source tool.

Key Implementation Details:

Robust Type Detection: The client-side implementation in RuntimeService.mjs uses Neo.typeOf(cls) to correctly differentiate between NeoClass (using cls.prototype) and NeoInstance (using cls.constructor.prototype). This ensures it works for both standard classes and singletons (like Neo.worker.App).

Source Retrieval: Uses Function.prototype.toString() to retrieve the exact runtime source code of the method.

Workflow: This tool is explicitly documented in OpenAPI as the prerequisite step for the patch_code tool, enabling a safe "read-modify-write" hot-patching cycle.

Full Stack: Exposed via Neo.ai.Client mapping and the Neural Link MCP Server proxy.

tobiu closed this issue on Jan 4, 2026, 2:07 PM