RAG-Powered Agent

AI agent that uses retrieval-augmented generation as a tool. The agent reasons and acts, the RAG pipeline provides grounded knowledge from a document corpus.

Name	rag-agent
Version	0.1.0
Tags	ai, rag, agent, retrieval
Source	composites/rag-agent.yaml

Render it

# CLI
npx @nanohype/sdk render-composite rag-agent --out ./my-app

# SDK
import { LocalSource, renderComposite } from "@nanohype/sdk";
const result = await renderComposite(source, "rag-agent", variables);

# MCP — from an agent
get_composite({ name: "rag-agent" })

What it draws together

Template	Rendered at	Notes
monorepo	root	the root project
agentic-loop	packages/agent
rag-pipeline	packages/rag
ts-service	apps/api
module-auth-ts	packages/auth
module-database-ts	packages/db
module-storage-ts	packages/storage
eval-harness	packages/evals
k8s-deploy	infra

Variables

Required

ProjectName string

Project name Must be lowercase kebab-case.

Optional

LlmProvider string — defaults to anthropic

LLM provider

VectorStore string — defaults to pgvector

Vector database backend