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	8341
title	Robust Knowledge Base Delta Updates (Hash-based IDs + Deterministic Sorting)
state	Closed
labels	bugenhancementai
assignees	tobiu
createdAt	Jan 5, 2026, 11:27 PM
updatedAt	Jan 5, 2026, 11:36 PM
githubUrl	https://github.com/neomjs/neo/issues/8341
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 5, 2026, 11:36 PM

Robust Knowledge Base Delta Updates (Hash-based IDs + Deterministic Sorting)

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

Closed v11.19.0 bugenhancementai

tobiu commented on Jan 5, 2026, 11:27 PM

The current Knowledge Base embedding logic relies on positional IDs (id_${index}) and OS-dependent file ordering (fs.readdir).

The Problem:

Indeterminism: fs.readdir returns files in arbitrary order. If the order changes (e.g., different OS), indices shift, causing a full re-embedding.
Cascading Invalidations: Inserting a single document shifts the index of all subsequent documents. This forces a re-upload of potentially the entire dataset, defeating the purpose of delta updates.

The Solution:

Hash-based IDs: Update VectorService.mjs to use chunk.hash as the ChromaDB Record ID instead of id_${index}. This makes IDs content-addressable and position-independent.
Deterministic Sorting: Enforce alphabetical sorting in all Source extractors (ApiSource, TicketSource, ReleaseNotesSource, TestSource, LearningSource). This ensures the generated ai-knowledge-base.jsonl file remains stable in Git history.

Implementation Plan:

Refactor VectorService.embed() to index existing documents by ID (which will now be the hash).
Update Sources to sort files/keys before writing.

tobiu added the bug label on Jan 5, 2026, 11:27 PM

tobiu added the enhancement label on Jan 5, 2026, 11:27 PM

tobiu added the ai label on Jan 5, 2026, 11:27 PM

tobiu assigned to @tobiu on Jan 5, 2026, 11:34 PM

tobiu referenced in commit 6100d61 - "Enhancement: Robust Knowledge Base Delta Updates #8341 on Jan 5, 2026, 11:36 PM

tobiu Jan 5, 2026, 11:36 PM

Input from Gemini 3 Pro:

✦ I have implemented the proposed changes:

VectorService.mjs:

Switched from positional IDs (id_${index}) to Hash-based IDs (chunk.hash). This ensures that inserting a new document doesn't invalidate the IDs of all subsequent documents.

Implemented batched fetching (limit: 2000) for retrieving existing IDs from ChromaDB to ensure scalability with large collections (addressing the 10k+ document scenario).

Simplified the diffing logic to check for hash existence directly.

Source Extractors:

ApiSource.mjs: Added sorting by name.

TicketSource.mjs: Added sorting for both release version directories and ticket files.

ReleaseNotesSource.mjs: Added sorting for release note files.

TestSource.mjs: Added sorting for directory entries.

These changes ensure that the Knowledge Base generation is deterministic and that updates are true deltas, minimizing unnecessary re-embeddings.

tobiu closed this issue on Jan 5, 2026, 11:36 PM