What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

Why is Neo.mjs called an Application Engine instead of a framework?

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	7904
title	Refactor Knowledge Base embedding logic into Vector Service
state	Closed
labels	airefactoring
assignees	tobiu
createdAt	Nov 25, 2025, 5:19 PM
updatedAt	Nov 25, 2025, 6:29 PM
githubUrl	https://github.com/neomjs/neo/issues/7904
author	tobiu
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Nov 25, 2025, 6:29 PM

Refactor Knowledge Base embedding logic into Vector Service

Closed v11.11.0/archive-v11-11-0-chunk-1 airefactoring

tobiu commented on Nov 25, 2025, 5:19 PM

Goal: Further simplify DatabaseService.mjs by extracting the embedding generation and vector database upsert logic into a dedicated service.

Current State: embedKnowledgeBase is a complex method (~160 lines) that mixes:

Business Logic: Calculating class inheritance chains, hashing chunks, and diffing against the existing database.
Integration Logic: Interacting with the Google Generative AI API for embeddings and the ChromaDB client for storage.

Proposed Architecture:

Create a new service (e.g., services/VectorService.mjs or services/EmbeddingService.mjs).
Move the heavy lifting of the "ETL Load" phase to this service.

Impact: DatabaseService will become a pure lifecycle manager and orchestrator, delegating:

Extraction to source/* providers.
Loading/Embedding to the new VectorService. This completes the separation of concerns for the Knowledge Base.

tobiu added the ai label on Nov 25, 2025, 5:19 PM

tobiu added the refactoring label on Nov 25, 2025, 5:19 PM

tobiu assigned to @tobiu on Nov 25, 2025, 6:28 PM

tobiu referenced in commit 227b7ae - "Refactor Knowledge Base embedding logic into Vector Service #7904" on Nov 25, 2025, 6:29 PM

tobiu closed this issue on Nov 25, 2025, 6:29 PM