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	8929
title	Feat: Implement Unit Test Agent Workflow (.agent/workflows/unit-test.md)
state	Closed
labels	documentationdeveloper-experienceai
assignees	tobiu
createdAt	Jan 31, 2026, 10:16 PM
updatedAt	Jan 31, 2026, 10:41 PM
githubUrl	https://github.com/neomjs/neo/issues/8929
author	tobiu
commentsCount	1
parentIssue	8925
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 31, 2026, 10:41 PM

Feat: Implement Unit Test Agent Workflow (.agent/workflows/unit-test.md)

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

Closed v12.0.0 documentationdeveloper-experienceai

tobiu commented on Jan 31, 2026, 10:16 PM

Create a specialized startup profile for AI agents focused on unit testing.

File: .agent/workflows/unit-test.md

Content Requirements:

Context Injection: Instructions to read src/Neo.mjs and src/core/Base.mjs.
Domain Knowledge: Instructions to read learn/guides/testing/UnitTesting.md.
Directives:
- Framework: Explicitly specify Playwright (running in Node.js mode) as the harness.
- Architecture: Explain the "Single-Thread Simulation" concept (App+VDom in one thread).
- Critical Rules:
  - Mandatory import of src/core/_export.mjs.
  - Unique class names per test file (Namespace Isolation).
- Commands: Use npm run test-unit or the specific file command: npx playwright test path/to/spec.mjs -c test/playwright/playwright.config.unit.mjs.

Goal: Enable an agent to instantly switch context to "Unit Test Mode" without manual prompting.

tobiu added the documentation label on Jan 31, 2026, 10:16 PM

tobiu added the developer-experience label on Jan 31, 2026, 10:16 PM

tobiu added the ai label on Jan 31, 2026, 10:16 PM

tobiu added parent issue #8925 on Jan 31, 2026, 10:16 PM

tobiu referenced in commit 13faa8b - "feat: Implement Unit Test Agent Workflow (#8929)" on Jan 31, 2026, 10:40 PM

tobiu Jan 31, 2026, 10:41 PM

Input from Gemini 3 Pro:

✦ I have successfully implemented the Unit Test Specialist workflow.

Completed Actions:

Created .agent/workflows/unit-test.md: Defines the rigorous "Single-Thread Simulation" protocol, mandatory readings, and precise execution commands.

Updated .gitignore: Removed the rule ignoring the .agent folder to ensure workflows are version controlled.

Updated learn/guides/testing/UnitTesting.md: Added documentation for the clean npm run test-unit -- <file> command pattern.

Pushed to dev: All changes are committed under (#8929).

The foundation for specialized testing agents is now live. I will close this ticket.

tobiu assigned to @tobiu on Jan 31, 2026, 10:41 PM

tobiu closed this issue on Jan 31, 2026, 10:41 PM