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	9750
title	Fix Prio 0 swarm boot sequence & plan file-system MCP server
state	Closed
labels	bugenhancementai
assignees	tobiu
createdAt	Apr 7, 2026, 12:13 PM
updatedAt	Apr 7, 2026, 1:07 PM
githubUrl	https://github.com/neomjs/neo/issues/9750
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 7, 2026, 12:40 PM

Fix Prio 0 swarm boot sequence & plan file-system MCP server

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

Closedbugenhancementai

tobiu commented on Apr 7, 2026, 12:13 PM

Prio 0 Architectural Fix: Subagents and test harnesses were improperly calling await instance.initAsync() instead of subscribing to the ready() promise. This has been corrected.
Knowledge Base Enhancement (Anchor & Echo): Added explicit warnings in src/core/Base.mjs to JSDocs for initAsync and ready so future AI agents (Gemma4/Librarian) natively understand the framework lifecycle.
Core Tooling Extension: Subagents require the ability to read files to avoid UI component hallucination. We will construct a new standalone MCP server (ai/mcp/server/file-system/) for raw tooling, rather than bloating the knowledge-base engine.
Cleanup: Delete obsolete ai/swarm/qa-test.mjs PoC in favor of test/playwright/unit/ai/agent/QA.spec.mjs.

tobiu added the bug label on Apr 7, 2026, 12:13 PM

tobiu added the enhancement label on Apr 7, 2026, 12:13 PM

tobiu added the ai label on Apr 7, 2026, 12:13 PM

tobiu referenced in commit 07c3bd7 - "feat: Fix Prio 0 swarm boot sequence & update JSDocs (#9750)" on Apr 7, 2026, 12:16 PM

tobiu referenced in commit 5db53c3 - "feat: Implement ai/mcp/server/file-system foundation & baseline tools (#9750)" on Apr 7, 2026, 12:40 PM

tobiu assigned to @tobiu on Apr 7, 2026, 12:40 PM

tobiu Apr 7, 2026, 12:40 PM

We successfully implemented the file-system MCP server and mapped it to the MCP client configuration. The QA subagent swarm has been updated to use this new file-system server. The playbook is functionally working via the Playwright unit tests. Closing the ticket as the PoC is complete.

tobiu closed this issue on Apr 7, 2026, 12:40 PM

tobiu referenced in commit 65368bb - "feat: Global Anti-Hallucination Policy injection in Swarm topology (#9750)" on Apr 7, 2026, 1:06 PM

tobiu Apr 7, 2026, 1:07 PM

Input from Antigravity (Gemini 3.1 Pro):

✦ The local File-System MCP and Swarm node architecture is complete and hardened!

Key Changes:

Built a containerized local backend for MCP file access strictly jailed to the Neo project workspace.

Corrected the initAsync() architectural redundancy bugs.

Created a global Swarm Anti-Hallucination Policy in the local Node pipeline enforcing sub-agents to trace files before generating assumptions.

Resolved Gemma4 Swarm Node test integration (achieved green tests with native neo-mjs unit testing paradigms and Playwright execution).

This hardens the final framework infrastructure requirements mapping theoretical multi-agent context directly into safe Node execution pipelines.