# ykhli/local-ai-stack

A starter kit to build *local-only* AI apps that cost $0 to run -- starting with document Q&A. Written in Javascript

Repository: https://github.com/ykhli/local-ai-stack
Canonical: https://ross.abutalabs.com/products/local-ai-stack
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2024-01-30T06:15:57+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 74
- inputs: {"age_days": 1037, "days_push": 946, "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 1391, forks 190 (observed 2026-08-28T04:04:35.915968+00:00)

## What it is
A starter kit (boilerplate) for building fully local AI applications with zero API costs, beginning with a document Q&A chat app. It combines Ollama for local LLM inference, Supabase pgvector as a local vector database, LangChain.js for orchestration, and Transformers.js for embeddings, all wired into a Next.js frontend.

## Use cases
- build a document Q&A app that runs entirely locally
- chat with my own documents without sending data to the cloud
- get a free $0-cost local AI stack up and running
- learn how to combine Ollama, Supabase pgvector, and LangChain
- prototype a private RAG app on my laptop
- generate embeddings locally with transformers.js

## When to choose
- you want a working local-only RAG app with no API keys or credit card
- privacy matters and documents must never leave your machine
- you want a Next.js + LangChain.js codebase to extend into your own AI app
- you already use or want to learn Ollama and Supabase locally

## When to avoid
- you need production-grade scalability or hosted deployment out of the box
- you want a polished end-user product rather than a developer starter kit
- you prefer Python-based AI stacks over JavaScript/TypeScript
- you need multi-user auth and cloud vector stores without extra setup

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, llm-inference, vector-database, chat-interface, web-framework
- domain: artificial-intelligence, large-language-models, self-hosted, developer-tools
- platform: self-hosted, cross-platform
- tags: local-ai, ollama, supabase, langchain, nextjs, starter-kit, privacy, document-qa, transformers-js, boilerplate, retrieval-augmented-generation, nodejs, docker

## Member repositories
- ykhli/local-ai-stack (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:35.915968+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 2026-08-30T08:33:13.413990+00:00, confidence not recorded.
  - readme: https://github.com/ykhli/local-ai-stack (fetched 2026-08-28T04:04:35.915968+00:00, sha 9b689cdc6356)
- Data as of 2026-08-30T08:39:29.467469+00:00.