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	7917
title	Feat: Create ''Dev Agent'' MVP (Ticket -> PR)
state	Closed
labels	enhancementai
assignees	[]
createdAt	Nov 29, 2025, 4:09 PM
updatedAt	Nov 29, 2025, 10:44 PM
githubUrl	https://github.com/neomjs/neo/issues/7917
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 29, 2025, 10:44 PM

Feat: Create 'Dev Agent' MVP (Ticket -> PR)

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

Closed v11.14.0 enhancementai

tobiu commented on Nov 29, 2025, 4:09 PM

Feat: Create 'Dev Agent' MVP (Ticket -> PR)

Context

This is the execution arm of the "Feature Factory" experiment (Epic #7914). Once a PM Agent has created technical tickets, we need a "Developer Agent" to pick them up and implement the code.

Goal

Create a standalone Node.js script ai/agents/dev.mjs that acts as a "Headless Developer Agent."

Requirements

1. Input

The script must accept an Issue Number as a CLI argument: node ai/agents/dev.mjs --issue 456
(Future enhancement: Polling mode that scans for agent-task:pending)

2. Logic (The "Brain")

Read: Fetch the Issue body (YAML contract) to understand the requirements.
Explore: Use codebase_investigator or search_file_content (via SDK) to locate relevant files.
Implement: Use read_file / write_file to modify the code.
Verify: Run tests (if specified in the ticket) to ensure correctness.

3. Output (Execution)

Commit: Create a new branch feature/issue-456.
Push: Push changes to the repository.
PR: Create a Pull Request linking to the original issue.
Update Status: Update the issue labels to agent-task:completed (or agent-task:blocked if it failed).

Tech Stack

Use ai/services.mjs for the AI logic.
Use simple-git or shell commands for Git operations.
Adhere strictly to the ai/agents/PROTOCOL.md state machine.

tobiu added the enhancement label on Nov 29, 2025, 4:09 PM

tobiu added the ai label on Nov 29, 2025, 4:09 PM

tobiu cross-referenced by #7914 on Nov 29, 2025, 5:24 PM

tobiu Nov 29, 2025, 10:18 PM

Input from Gemini 2.5:

✦ Implementation Update: Adopting the "Fake Agent" pattern to accelerate the MVP.

Architecture: The agent is a standalone Node.js script using direct imports from ai/services.mjs.

Context: The agent now consumes the full raw markdown content of the issue (including frontmatter) to provide maximum context to the LLM.

Execution: Uses child_process for Git operations and GoogleGenerativeAI for code generation.

tobiu Nov 29, 2025, 10:43 PM

Feature Factory Success: The MVP is operational.

Executed on Test Issue #7933.
Created Branch .
Modified .
Submitted PR #7934.

The infrastructure () has been pushed to . Closing this implementation ticket.

tobiu closed this issue on Nov 29, 2025, 10:44 PM