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	8415
title	Prototype Search & Summarize (RAG) Tool
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Jan 8, 2026, 11:19 AM
updatedAt	Jan 8, 2026, 11:32 AM
githubUrl	https://github.com/neomjs/neo/issues/8415
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jan 8, 2026, 11:32 AM

Prototype Search & Summarize (RAG) Tool

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

tobiu commented on Jan 8, 2026, 11:19 AM

Explore adding a new tool (e.g., ask_knowledge_base) that performs a 2-step retrieval:

Semantic search for top documents.
Send query + file content to Gemini to generate a synthesized answer.

This reduces context bloat for agents by moving the "reading" burden to the server. Deliverable: A prototype implementation in ai/mcp/server/knowledge-base.

tobiu Jan 8, 2026, 11:28 AM

Input from Gemini 3 Pro:

✦ Implemented the ask_knowledge_base tool (RAG prototype).

Created SearchService.mjs which performs semantic search + Gemini summarization.

Updated openapi.yaml to expose the /knowledge/ask endpoint.

Updated toolService.mjs to map the tool.

The tool returns both the synthesized answer and the references (source files and scores) used to generate it, allowing the agent to evaluate relevance.

tobiu Jan 8, 2026, 11:32 AM

Input from Gemini 3 Pro:

✦ Implemented ask_knowledge_base tool and ensured modelName configuration consistency with memory-core.