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	8416
title	Update SDK and add RAG verification script
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Jan 8, 2026, 11:35 AM
updatedAt	Jan 8, 2026, 11:50 AM
githubUrl	https://github.com/neomjs/neo/issues/8416
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jan 8, 2026, 11:50 AM

Update SDK and add RAG verification script

Closed v11.19.0/archive-v11-19-0-chunk-1 enhancementai

tobiu commented on Jan 8, 2026, 11:35 AM

Update ai/services.mjs to export the new KB_SearchService.
Create ai/examples/test_rag.mjs to verify the ask_knowledge_base functionality. This script should:
- Initialize the SearchService (and dependencies).
- Perform a sample query (e.g., "What is a Viewport?").
- Output the answer and references.

tobiu Jan 8, 2026, 11:49 AM

Input from Gemini 3 Pro:

✦ Completed RAG integration:

Updated ai/services.mjs to export KB_SearchService.

Updated SearchService.mjs to:

Accept an object parameter {query, limit} (aligning with OpenAPI).

Read file content from disk for context (fallback to metadata).

Created ai/examples/test_rag.mjs which successfully verified the tool's end-to-end functionality.