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	7836
title	Refactor: Robust Hybrid Database Lifecycle for AI Services
state	Closed
labels	enhancementairefactoring
assignees	tobiu
createdAt	Nov 21, 2025, 2:31 AM
updatedAt	Nov 21, 2025, 3:14 AM
githubUrl	https://github.com/neomjs/neo/issues/7836
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 21, 2025, 3:14 AM

Refactor: Robust Hybrid Database Lifecycle for AI Services

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

Closed v11.8.0 enhancementairefactoring

tobiu commented on Nov 21, 2025, 2:31 AM

Objective Refactor the DatabaseLifecycleService and ChromaManager to robustly support a hybrid database model (External, Managed, Shared) without race conditions or deadlocks.

Context The current lifecycle implementation (ai/mcp/server/knowledge-base/services/DatabaseLifecycleService.mjs) has a potential circular dependency and timing issue:

DatabaseLifecycleService waits for ChromaManager to be ready.
ChromaManager attempts to connect immediately.
If the DB is not running, ChromaManager fails to connect, but DatabaseLifecycleService hasn't started it yet.

We need to support:

External Mode: DB started manually in a terminal.
Managed Mode: Service starts the DB process.
Shared Mode: Multiple agents/processes sharing one DB instance (first one starts it, others detect it).

Tasks

Decouple Initialization: DatabaseLifecycleService should check for an existing DB before waiting for ChromaManager.
Robust Start: If no DB is detected, start the process and wait for the port to be responsive before declaring readiness.
Service Base Class: Implement Neo.ai.ServiceBase to standardize the ready() contract across all services (KB, Memory, GitHub), ensuring consumers (Agents) can just await Service.ready().

Deliverables

Refactored DatabaseLifecycleService.mjs (KB & Memory).
Refactored ChromaManager.mjs (KB & Memory).
New ai/core/ServiceBase.mjs.

tobiu added the enhancement label on Nov 21, 2025, 2:31 AM

tobiu added the ai label on Nov 21, 2025, 2:31 AM

tobiu added the refactoring label on Nov 21, 2025, 2:31 AM

tobiu assigned to @tobiu on Nov 21, 2025, 3:13 AM

tobiu Nov 21, 2025, 3:13 AM

Input from Gemini 3.0 Preview:

✦ I have successfully refactored the AI Service lifecycle to support a robust hybrid database model.

Key Changes:

Eliminated Circular Dependencies: DatabaseLifecycleService no longer statically imports ChromaManager. It uses dynamic imports to access the client for heartbeat checks, preventing startup crashes.

Enforced Initialization Order:

DatabaseLifecycleService: Starts the process and waits for a heartbeat (via http or dynamic client).

ChromaManager: Awaits DatabaseLifecycleService.ready() before attempting to connect.

SessionService / DatabaseService: Await ChromaManager.ready() before performing operations.

Simplified Agent SDK: The self-healing.mjs demo now simply awaits KB_LifecycleService.ready() and KB_ChromaManager.ready() (or just the manager) without manual retry loops.

This resolves the race conditions and supports external/shared database instances.

Closing ticket.

tobiu closed this issue on Nov 21, 2025, 3:14 AM

tobiu referenced in commit 74edfca - "refactor(ai): Robust Hybrid Database Lifecycle and Roadmap update (#7836)" on Nov 21, 2025, 9:51 AM

tobiu cross-referenced by #7837 on Nov 21, 2025, 10:14 AM