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	9719
title	Hybrid Vector DB: Decouple TextEmbeddingService and Eliminate Provider Fallbacks
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Apr 5, 2026, 11:41 AM
updatedAt	Apr 5, 2026, 11:43 AM
githubUrl	https://github.com/neomjs/neo/issues/9719
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 5, 2026, 11:42 AM

Hybrid Vector DB: Decouple TextEmbeddingService and Eliminate Provider Fallbacks

Closed v13.0.0/archive-v13-0-0-chunk-2 enhancementai

tobiu commented on Apr 5, 2026, 11:41 AM

Problem

The TextEmbeddingService relied on a global fallback aiConfig.embeddingProvider alongside engine-specific configs (chromaEmbeddingProvider and neoEmbeddingProvider). This created ambiguity, caused potential API key requirement issues (GEMINI_API_KEY being required even if local embeddings are preferred), and prevented a clean both engine mode setup from operating correctly since both storage managers shared the same fallback context.

Solution

Removed the global embeddingProvider from config.mjs to eliminate fallback ambiguity.
Refactored TextEmbeddingService to require explicit provider declaration via embedText(text, explicitProvider).
Updated ChromaManager and SQLiteVectorManager to strictly supply their respective embedding engine requirements to the TextEmbeddingService.
Corrected HealthService API key checks to properly identify chroma vs neo engine requirements without assuming gemini based on a global fallback.

tobiu added the enhancement label on Apr 5, 2026, 11:41 AM

tobiu added the ai label on Apr 5, 2026, 11:41 AM

tobiu referenced in commit 6b95c8f - "refactor(ai): Hybrid Vector DB: Decouple TextEmbeddingService and Eliminate Provider Fallbacks (#9719)" on Apr 5, 2026, 11:42 AM

tobiu assigned to @tobiu on Apr 5, 2026, 11:42 AM

tobiu Apr 5, 2026, 11:42 AM

Fix committed locally and pushed to the repository. The implementation removes the global fallback and enforces rigorous provider configurations in , ensuring deterministic routing in engine setups.

tobiu closed this issue on Apr 5, 2026, 11:42 AM

tobiu Apr 5, 2026, 11:43 AM

Fix committed locally and pushed to the repository. The implementation removes the global embeddingProvider fallback and enforces rigorous provider configurations in TextEmbeddingService, ensuring deterministic routing in both engine setups.

2026-05-06T09:00:58Z @neo-gpt cross-referenced by #10804
2026-05-06T09:22:17Z @neo-gpt cross-referenced by PR #10810