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	8194
title	Feat: Neural Link - Propagate Runtime Errors to Agent
state	Closed
labels	bugenhancementai
assignees	tobiu
createdAt	Dec 28, 2025, 11:17 PM
updatedAt	Dec 28, 2025, 11:20 PM
githubUrl	https://github.com/neomjs/neo/issues/8194
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 28, 2025, 11:20 PM

Feat: Neural Link - Propagate Runtime Errors to Agent

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

Closed v11.18.0 bugenhancementai

tobiu commented on Dec 28, 2025, 11:17 PM

Context: The current Neo.ai.Client.onSocketMessage implementation catches errors but only logs them to the console. It does not send an error response back to the Neural Link server.

Problem: If handleRequest throws (e.g., "Component not found"), the server hangs waiting for a response that never comes. The agent perceives this as a timeout or a broken tool.

Requirement:

Wrap handleRequest in a try...catch.
In the catch block, call sendResponse(data.id, {error: e.message}) (or a similar error structure compliant with JSON-RPC 2.0).
Ensure the server handles JSON-RPC error responses correctly.

Goal: Ensure agents receive explicit error feedback when a runtime operation fails.

tobiu added the bug label on Dec 28, 2025, 11:17 PM

tobiu added the enhancement label on Dec 28, 2025, 11:17 PM

tobiu added the ai label on Dec 28, 2025, 11:17 PM

tobiu assigned to @tobiu on Dec 28, 2025, 11:18 PM

tobiu added parent issue #8169 on Dec 28, 2025, 11:18 PM

tobiu referenced in commit 7272d52 - "feat(ai): Propagate runtime errors to agent (#8194) on Dec 28, 2025, 11:19 PM

tobiu Dec 28, 2025, 11:20 PM

Input from Gemini:

✦ I have implemented error propagation for the Neural Link.

Changes in src/ai/Client.mjs:

Enhanced onSocketMessage: Now wraps handleRequest in a try...catch block.

Added sendError: Sends a JSON-RPC 2.0 error response (Code -32603) with the exception message and stack trace.

Benefit: Agents will now receive immediate, descriptive feedback when a tool call fails (e.g., "Component not found"), enabling self-correction instead of timeouts.

tobiu closed this issue on Dec 28, 2025, 11:20 PM