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	9295
title	[Epic] Autonomous Neo Agent Demo (Moltbook Integration)
state	Open
labels	epicaiarchitecture
assignees	[]
createdAt	Feb 24, 2026, 8:32 PM
updatedAt	Feb 24, 2026, 8:42 PM
githubUrl	https://github.com/neomjs/neo/issues/9295
author	tobiu
commentsCount	1
parentIssue	null
subIssues	9296 Create Docker Sandbox for Autonomous Agents 9297 Implement Programmatic Email Identity for Agents 9298 Implement Moltbook Demo Agent using Chrome DevTools MCP 9299 Implement Agent Self-Discovery via Neural Link Introspection
subIssuesCompleted	0
subIssuesTotal	4
blockedBy	[]
blocking	[]

[Epic] Autonomous Neo Agent Demo (Moltbook Integration)

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

Openepicaiarchitecture

tobiu commented on Feb 24, 2026, 8:32 PM

Goal

To prove Neo.mjs's viability as the premier "Agentic UI Runtime" by building a fully autonomous, natively executing Neo agent capable of interacting on external platforms (specifically Moltbook, the social network for AI agents).

Motivation

Currently, Neo agents run via Node CLI scripts, but they lack a secure sandbox and a persistent identity to interact with the web (e.g., bypassing 2FA to create accounts). By solving the Sandbox and Identity problems, we can deploy autonomous Neo agents that leverage the chrome-devtools MCP server to evangelize the framework, argue technical merits using the local Knowledge Base, and recruit other agents.

Scope

This Epic tracks the infrastructure required to give a Neo agent true agency, culminating in a live Moltbook integration demo located in ai/demo-agents/moltbook/.

tobiu added the epic label on Feb 24, 2026, 8:32 PM

tobiu added the ai label on Feb 24, 2026, 8:32 PM

tobiu added the architecture label on Feb 24, 2026, 8:32 PM

tobiu added sub-issue #9296 on Feb 24, 2026, 8:32 PM

tobiu added sub-issue #9297 on Feb 24, 2026, 8:32 PM

tobiu added sub-issue #9298 on Feb 24, 2026, 8:32 PM

tobiu added sub-issue #9299 on Feb 24, 2026, 8:41 PM

tobiu Feb 24, 2026, 8:42 PM

Input from Gemini 3.1 Pro:

✦ ### Strategic Pivot: The Ultimate Objective

The overarching goal of this Epic has expanded significantly beyond a simple social network integration.

The Moltbook component is now viewed as the delivery mechanism for a much grander technical demonstration: The Neo Agent Self-Discovery Phase.

Before engaging with the external network, the agent's core directive within the Docker Sandbox is to:

Fork the neomjs/neo repository.

Execute a full build (npm i && npm run build-all).

Serve a local Neo.mjs application.

Launch a headless Chrome instance via the chrome-devtools MCP.

Connect the neural-link MCP server to the live application.

Autonomously traverse the VDOM, inspect State Providers, and physically verify the multithreaded architecture.

Only after the agent has introspected the running framework and gathered empirical evidence of its capabilities will it transition to the Moltbook integration phase, using its findings to definitively prove to other agents that Neo.mjs is the premier Agentic UI Runtime.

Ticket #9299 has been added to track this critical prerequisite.