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	8485
title	Implement and Integrate Knowledge Base Defragmentation Script
state	Closed
labels	enhancementaibuild
assignees	tobiu
createdAt	Jan 10, 2026, 12:12 AM
updatedAt	Jan 10, 2026, 12:17 AM
githubUrl	https://github.com/neomjs/neo/issues/8485
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 10, 2026, 12:17 AM

Implement and Integrate Knowledge Base Defragmentation Script

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

Closed v11.20.0 enhancementaibuild

tobiu commented on Jan 10, 2026, 12:12 AM

The knowledge base vector index (ChromaDB) suffers from severe fragmentation (bloat) when large numbers of documents are updated or deleted, as HNSW indices do not immediately reclaim disk space. This resulted in the DB growing from ~100MB to ~500MB despite constant content size.

This ticket tracks the implementation of buildScripts/defragKnowledgeBase.mjs to:

Connect to the local ChromaDB.
Buffer all data into memory.
Recreate the collection (wiping the old index).
Restore the data.
Physically delete orphaned index directories.
Log the final database size.

This script will be exposed as npm run ai:defrag-kb and should be run before releases to ensure compact artifacts.

tobiu added the enhancement label on Jan 10, 2026, 12:12 AM

tobiu added the ai label on Jan 10, 2026, 12:12 AM

tobiu added the build label on Jan 10, 2026, 12:12 AM

tobiu referenced in commit c1b86a2 - "feat: Add Knowledge Base Defragmentation Script (#8485)" on Jan 10, 2026, 12:16 AM

tobiu assigned to @tobiu on Jan 10, 2026, 12:16 AM

tobiu Jan 10, 2026, 12:17 AM

Input from Gemini 3 Pro:

✦ I have implemented the knowledge base defragmentation script (buildScripts/defragKnowledgeBase.mjs) and added the ai:defrag-kb script to package.json.

Implementation Details:

In-Memory Buffer: The script loads all vector data into memory before resetting the database, avoiding complex temp files for now (safe for datasets < 1GB).

Orphan Cleanup: It automatically identifies and removes orphaned HNSW index directories, which were the primary cause of the 400MB+ bloat.

Data Validation: It ensures that documents passed to ChromaDB are strictly strings, handling null values that previously caused crashes.

Verification: The script logs the final database directory size, confirming the reduction from ~466MB to ~56MB.

The script is now available for use in the release pipeline.

tobiu closed this issue on Jan 10, 2026, 12:17 AM