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	7839
title	Enhance AI SDK: Fix ChromaDB warnings and enable programmable backups
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Nov 21, 2025, 11:16 AM
updatedAt	Nov 21, 2025, 11:18 AM
githubUrl	https://github.com/neomjs/neo/issues/7839
author	tobiu
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 21, 2025, 11:18 AM

Enhance AI SDK: Fix ChromaDB warnings and enable programmable backups

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

Closed v11.8.0 enhancementai

tobiu commented on Nov 21, 2025, 11:16 AM

This issue consolidates several related changes aimed at improving the stability and usability of the AI infrastructure SDK.

1. Fix ChromaDB Embedding Function Warning The ChromaDB client emits a persistent warning ("No embedding function configuration found") because our dummyEmbeddingFunction was too simple and flagged as "legacy".

Change: Update dummyEmbeddingFunction in ai/mcp/server/*/config.mjs to fully implement the IEmbeddingFunction interface (adding name, getConfig, buildFromConfig) with clear intent-driven comments explaining why.

2. Enable Database Backup/Restore via SDK The Memory_DatabaseService was not exposed in the public SDK, preventing agents from programmatically triggering backups.

Change: Export Memory_DatabaseService in ai/services.mjs.
Change: Update Memory_DatabaseService to allow optional paths for export, defaulting to the config.
Change: Fix relative path issues in ai/mcp/server/memory-core/config.mjs by using __dirname to ensure backups work regardless of the execution context (npm run vs node).

3. Refactor Import Logic

Change: Update importDatabase in Memory_DatabaseService to cleanly handle collection clearing (replace mode) without using ternary operators, improving readability.

4. Cleanup Example Scripts

Change: Remove redundant LifecycleService.ready() calls in ai/examples/self-healing.mjs (since ChromaManager.ready() now handles it).
New Artifacts: Add ai/examples/db-backup.mjs and ai/examples/db-restore.mjs as working proofs of the new SDK capabilities.

tobiu added the enhancement label on Nov 21, 2025, 11:16 AM

tobiu added the ai label on Nov 21, 2025, 11:16 AM

tobiu referenced in commit 33f1fe8 - "chore: Enhance AI SDK (Issue #7839) on Nov 21, 2025, 11:17 AM

tobiu assigned to @tobiu on Nov 21, 2025, 11:17 AM

tobiu closed this issue on Nov 21, 2025, 11:18 AM

tobiu cross-referenced by #7838 on Nov 21, 2025, 11:19 AM