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	8192
title	Feat: Neural Link - Log & Error Streaming
state	Closed
labels	enhancementaiarchitecture
assignees	tobiu
createdAt	Dec 28, 2025, 10:32 PM
updatedAt	Jan 3, 2026, 11:15 PM
githubUrl	https://github.com/neomjs/neo/issues/8192
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 3, 2026, 11:15 PM

Feat: Neural Link - Log & Error Streaming

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

Closed v11.18.0 enhancementaiarchitecture

tobiu commented on Dec 28, 2025, 10:32 PM

Context: Agents are "blind" to runtime errors they trigger. They need to see the App Worker's console output and exceptions to self-correct.

Scope:

App Worker Enhancement:
- Implement a log interceptor (hook console.* and globalThis.onerror).
- Forward logs to Main Thread -> Neural Link.
Neural Link Server Enhancement:
- ConnectionService: Receive log messages. Store in a ring buffer (e.g., last 1000 logs per session).
- Tool: get_console_logs(sessionId, filter). Returns the logs.
- Streaming: Optionally, explore MCP Notifications to push logs to the agent in real-time.

Goal: Provide runtime observability to the agent.

tobiu added the enhancement label on Dec 28, 2025, 10:32 PM

tobiu added the ai label on Dec 28, 2025, 10:32 PM

tobiu added the architecture label on Dec 28, 2025, 10:32 PM

tobiu added parent issue #8169 on Dec 28, 2025, 10:32 PM

tobiu assigned to @tobiu on Jan 3, 2026, 11:00 PM

tobiu referenced in commit 329a296 - "feat(ai): Implement Neural Link Log & Error Streaming (#8192) on Jan 3, 2026, 11:14 PM

tobiu Jan 3, 2026, 11:15 PM

Input from Gemini:

✦ I have implemented the Log & Error Streaming feature.

Changes:

App Worker (src/worker/App.mjs): Added interceptConsole method which hooks into console.log, warn, error, info and globalThis.onerror. These are forwarded to the Neural Link via Neo.ai.Client.

Server (ConnectionService.mjs): Implemented a ring buffer (size 1000) per session to store incoming console_log notifications. Added getConsoleLogs method supporting type and message filtering.

Tool (toolService.mjs): Exposed get_console_logs tool.

OpenAPI: Updated spec with the new endpoint.

Capability: Agents can now verify runtime errors or inspect application logs to self-diagnose issues using get_console_logs.

tobiu closed this issue on Jan 3, 2026, 11:15 PM