# a16z-infra/ai-getting-started

A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs

Repository: https://github.com/a16z-infra/ai-getting-started
Canonical: https://ross.abutalabs.com/products/ai-getting-started
Homepage: https://ai-getting-started.com/
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2024-08-21T12:35:18+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 83
- inputs: {"age_days": 1175, "days_push": 742, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4141, forks 661 (observed 2026-08-28T04:08:36.294749+00:00)

## What it is
A JavaScript/TypeScript starter stack for building AI weekend projects, combining Next.js, Clerk auth, Pinecone/pgvector vector stores, LangChain.js, and OpenAI/Replicate models with Fly.io deployment configs. It serves as a reference template showing how the pieces fit together.

## Use cases
- build an ai chatbot weekend project
- get started with llm app development
- template for ai app with auth and vector database
- learn how to integrate openai and replicate in nextjs
- deploy an ai app to fly.io
- set up rag with pinecone or pgvector

## When to choose
- you want a batteries-included starting point for a small AI web app
- you want to learn how auth, vector stores, and LLM APIs fit together
- you want a deployable Next.js AI template

## When to avoid
- you need a production-grade, actively maintained framework
- you don't want third-party services like Clerk, Pinecone, or OpenAI
- you need fine-grained control over the stack architecture

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-inference, rag, auth, vector-database, web-framework
- domain: artificial-intelligence, large-language-models, web-development, developer-tools
- platform: cloud
- tags: ai-stack, starter-template, nextjs, langchain, weekend-projects, nodejs, typescript, web-server

## Member repositories
- a16z-infra/ai-getting-started (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:36.294749+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:58.680379+00:00, confidence not recorded.
  - readme: https://github.com/a16z-infra/ai-getting-started (fetched 2026-08-28T04:08:36.294749+00:00, sha 8209eadeb866)
- Data as of 2026-08-30T08:39:29.467469+00:00.