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	8103
title	[GitHub Workflow] Add syncOnStartup configuration
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 13, 2025, 1:46 PM
updatedAt	Dec 13, 2025, 2:06 PM
githubUrl	https://github.com/neomjs/neo/issues/8103
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 13, 2025, 2:06 PM

[GitHub Workflow] Add syncOnStartup configuration

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

Closed v11.17.0 enhancementai

tobiu commented on Dec 13, 2025, 1:46 PM

Objective

Add a syncOnStartup configuration option to the GitHub Workflow MCP server to automatically trigger a full sync when the server starts. This includes hardening the HealthService to handle concurrent checks during the chaotic startup phase.

Description

The GitHub Workflow server needs to sync issues on startup to ensure a fresh cache. Since both the Server and the SyncService will need to check system health during initialization, we must ensure they don't race and trigger parallel, redundant gh CLI processes.

Implementation Details

Config: Add syncOnStartup: true to ai/mcp/server/github-workflow/config.mjs.
HealthService (ai/mcp/server/github-workflow/services/HealthService.mjs):
- Implement In-Flight Deduplication:
  - Add a private field (e.g., #healthCheckPromise) to store the pending check.
  - In healthcheck(), if a check is in progress, return the existing promise.
  - If not, start this.#performHealthCheck(), store the promise, and clear it upon completion/failure.
SyncService (ai/mcp/server/github-workflow/services/SyncService.mjs):
- Implement initAsync().
- Check aiConfig.syncOnStartup.
- Call await HealthService.healthcheck().
- Condition:
  - If status === 'healthy': Call await this.runFullSync().
  - If status !== 'healthy': Log a warning ("Skipping startup sync: GitHub CLI unhealthy") and return.
- Safety: Wrap in try/catch to prevent service crash on sync failure.
Server (ai/mcp/server/github-workflow/Server.mjs):
- Import SyncService.
- In initAsync, add await SyncService.ready() after the server's own health check. This ensures strict ordering: Server verifies environment -> SyncService completes (synced or skipped) -> Server opens for business.

tobiu added the enhancement label on Dec 13, 2025, 1:46 PM

tobiu added the ai label on Dec 13, 2025, 1:46 PM

tobiu assigned to @tobiu on Dec 13, 2025, 1:52 PM

tobiu referenced in commit 41a686e - "[GitHub Workflow] Add syncOnStartup configuration #8103" on Dec 13, 2025, 2:02 PM

tobiu Dec 13, 2025, 2:04 PM

Input from gemini:

✦ I have successfully implemented the syncOnStartup feature and hardened the startup sequence.

Changes:

Config: Added syncOnStartup: true to ai/mcp/server/github-workflow/config.mjs.

HealthService: Implemented In-Flight Deduplication for healthcheck(). This prevents the "thundering herd" problem where multiple services (Server & SyncService) trigger parallel gh CLI calls during startup.

SyncService: Added initAsync() logic to trigger runFullSync() on startup only if the system is healthy. It includes a try-catch block to ensure the service initializes even if the sync fails (e.g. network issues).

Server: Updated initAsync() to await SyncService.ready(). This ensures the server waits for the cache to be populated (or the attempt to finish) before accepting MCP tool requests.

The server is now robust against race conditions and will automatically keep the issue cache fresh.

tobiu closed this issue on Dec 13, 2025, 2:06 PM