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	9832
title	fix(ai): Resolve autonomous runSandman startup sequence race condition
state	Closed
labels	bugai
assignees	tobiu
createdAt	Apr 9, 2026, 8:27 PM
updatedAt	Apr 9, 2026, 8:28 PM
githubUrl	https://github.com/neomjs/neo/issues/9832
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 9, 2026, 8:28 PM

fix(ai): Resolve autonomous runSandman startup sequence race condition

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

Closedbugai

tobiu commented on Apr 9, 2026, 8:27 PM

The Problem

When running the ai:run-sandman pipeline (node ./buildScripts/ai/runSandman.mjs), the script synchronously blocks and fails with openAiCompatible server is not running if the LLM backend is not awake. This breaks autonomous workflows because it doesn't wait for the InferenceLifecycleService auto-boot orchestrator.

The Architectural Reality

In runSandman.mjs, the custom healthcheck checkProvider() is awaited before LifecycleService.ready() is invoked. Since the Inference daemon is bootstrapped inside SystemLifecycleService, the MLX or Ollama daemon never receives the command to start the background process before the script fatally exits.

Path Forward

We must refactor runSandman.mjs to await LifecycleService.ready() prior to polling the provider's health via checkProvider(). This guarantees the daemon lifecycle service has the opportunity to spawn the .venv or equivalent backend process.

tobiu added the bug label on Apr 9, 2026, 8:27 PM

tobiu added the ai label on Apr 9, 2026, 8:27 PM

tobiu referenced in commit 384768a - "fix(ai): Resolve autonomous runSandman startup sequence race condition (#9832)" on Apr 9, 2026, 8:28 PM

tobiu assigned to @tobiu on Apr 9, 2026, 8:28 PM

tobiu Apr 9, 2026, 8:28 PM

Input from Antigravity (Gemini):

✦ The runSandman.mjs startup pipeline has been successfully refactored. The checkProvider() validation strategy is now awaited after LifecycleService.ready(). This completely resolves the asynchronous dropping of the MLX auto-boot sequence, granting the Inference daemon orchestrator explicitly synchronous priority to start background LLM wrappers before polling for .json endpoints. Local ZSH configuration (which is purposefully unbound to dev history) was remediated independently.

tobiu closed this issue on Apr 9, 2026, 8:28 PM