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	7833
title	Demo: Self-Healing Repository Script (Agent OS)
state	Closed
labels	enhancementdeveloper-experienceai
assignees	tobiu
createdAt	Nov 21, 2025, 1:56 AM
updatedAt	Nov 21, 2025, 2:16 AM
githubUrl	https://github.com/neomjs/neo/issues/7833
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 21, 2025, 2:16 AM

Demo: Self-Healing Repository Script (Agent OS)

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

Closed v11.8.0 enhancementdeveloper-experienceai

tobiu commented on Nov 21, 2025, 1:56 AM

Objective Develop a proof-of-concept "Self-Healing" script that demonstrates the full power of the Agent OS SDK (ai/services.mjs). The script will autonomously simulate a bug fix workflow by interacting with GitHub issues, the Knowledge Base, and the Memory Core.

Context We have established the "Code Execution" infrastructure (#7831, #7832). The next step is to prove its value with a complex, multi-domain use case. This demo will serve as the canonical example for the "Agent OS" vision.

Workflow to Implement (ai/examples/self-healing.mjs)

Monitor: Use GH_IssueService to find an open issue labeled bug (or a specific test issue).
Understand: Use KB_QueryService to search for code and documentation relevant to the issue's title/body.
Plan: Use Memory_Service to log the agent's "thought process" and plan of attack.
Act (Simulation):
- In a real scenario, this would run tests.
- For this PoC, the script will "draft" a fix (e.g., generate a patch file or a comment) based on the retrieved context.
Report: Post a comment on the GitHub issue with the proposed solution and references to the docs used.

Deliverables

ai/examples/self-healing.mjs: The executable script.
Updates to ai/sdk-manifest.md if new patterns emerge.

Dependencies

Requires ai/services.mjs (Completed).
Requires a test issue in the repo to act upon.

tobiu added the enhancement label on Nov 21, 2025, 1:56 AM

tobiu added the developer-experience label on Nov 21, 2025, 1:56 AM

tobiu added the ai label on Nov 21, 2025, 1:56 AM

tobiu assigned to @tobiu on Nov 21, 2025, 1:57 AM

tobiu Nov 21, 2025, 2:16 AM

Input from Gemini 3.0 Preview:

I have successfully implemented and validated the "Self-Healing" demo script.

Deliverables:

ai/examples/self-healing.mjs: A fully autonomous script that monitors GitHub for bugs, queries the Knowledge Base for context, logs a plan to Memory, and posts a solution to the issue.
Validation: Ran the script against test issue #7834. The agent successfully identified DomEvents.md as the relevant context and posted a structured analysis comment.

This confirms that the "Agent OS" architecture (Unified SDK + Code Execution) allows agents to perform complex, multi-step maintenance tasks without human intervention.

Closing ticket.

tobiu closed this issue on Nov 21, 2025, 2:16 AM

tobiu referenced in commit e90762c - "feat(ai): Add Self-Healing Repository demo script (#7833)" on Nov 21, 2025, 9:51 AM