laoposkj

laoposkj / mastra-agentic-rag

Public

TypeScript AI agent with retrieval-augmented generation (RAG) using Mastra, Vercel AI SDK, OpenAI, and LibSQL/pgvector-ready — local-first RAG pipeline

agentic-rag ai-agents llm mastra openai
10
0
100% credibility
Found Apr 18, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

A starter template for creating AI agents using Mastra that intelligently retrieve and synthesize information from user-uploaded documents.

How It Works

1
🔍 Discover the starter kit

You stumble upon this ready-made kit for building a smart AI helper that pulls answers straight from your documents.

2
💻 Get it ready

Download everything to your computer and link up a thinking AI service to bring your helper to life.

3
📄 Feed in documents

Upload sample files or your own notes so your AI learns exactly what you need it to know.

4
🚀 Open the chat playground

Launch a simple web page where you can talk to your AI as if chatting with a knowledgeable friend.

5
💬 Ask away

Type questions about your documents and see the AI smartly search and reply with accurate info.

✅ Perfect answers every time

Your AI now confidently answers from your own knowledge base, making research fast and reliable.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is mastra-agentic-rag?

This TypeScript repo delivers a local-first RAG pipeline for Mastra agentic AI agents, letting models decide when to retrieve and refine queries from your docs. Developers get a production starter: npm install, ingest Markdown via CLI, then spin up Mastra Studio for chatting with the agent or running research workflows—all using OpenAI models, Vercel AI SDK, and LibSQL vectors on disk, no Docker required. It handles ingestion, semantic search, and grounded answers out of the box.

Why is it gaining traction?

As a typescript agent ai framework, it stands out with agentic RAG—agents call retrieval tools autonomously—and built-in evals for tool accuracy plus completeness, plus observability to Mastra Cloud. The hook is zero-infra dev: ingest sample docs in seconds, test workflows locally, build deploy bundles easily. TypeScript agents md fans appreciate the typed CLI scripts for ingest, dev server, and pgvector Docker option for scale.

Who should use this?

TypeScript developers building agentic RAG apps, like internal doc searchbots or research assistants on Mastra. Ideal for AI engineers prototyping typescript agent skills with OpenAI/Claude, or teams wanting a typescript agent library that skips vector DB setup. Skip if you need multi-provider vectors or heavy production traffic yet.

Verdict

Solid Mastra agentic rag starter with strong docs, full tests, and easy local setup—grab it for typescript agentic frameworks experiments despite 10 stars and 1.0% credibility score signaling early maturity. Fork and deploy if Mastra fits; otherwise, watch for growth.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.