JS Local-only AI Apps starter kit: cost $0 to run and test locally
Hi HN! Here's a local-only stack I built over the weekend - hope it can be useful for you! I have been building a lot of AI apps - https://github.com/a16z-infra/ai-town https://github.com/a16z-infra/companion-app ... And there were definitely times I spent way too much $$ before deploying the app to production. So I was looking for a "local only" stack and found a few tools that worked well together. I used the following set of tools but may add more options later: - Inference: Ollama - VectorDB: Supabase pg-vector - LLM orchestration: langchain -…
In plain words
This is a starter kit for building AI applications that run entirely locally without cloud costs. It combines Ollama for inference, Supabase's pg-vector for vector storage, LangChain for LLM orchestration, and Next.js for the framework. The kit is designed for developers who want to test and develop AI apps without spending money on cloud services or API calls, making it accessible to those without corporate budgets.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! Here's a local-only stack I built over the weekend - hope it can be useful for you! I have been building a lot of AI apps - https://github.com/a16z-infra/ai-town https://github.com/a16z-infra/companion-app ... And there were definitely times I spent way too much $$ before deploying the app to production. So I was looking for a "local only" stack and found a few tools that worked well together. I used the following set of tools but may add more options later: - Inference: Ollama - VectorDB: Supabase pg-vector - LLM orchestration: langchain - Framework: nextjs My learning from building ai-town was also that many people don't have the luxury of swiping a credit card to test an app with a lot of AI workloads -- not surprisingly, many models on Ollama are already very good - I used llama2-7b for majority of my dev work. Hope this can lower the barrier to entry for building AI apps. :)
Does the same job
all alternatives →
- LRLocalLLM – Recipes for Running the Local LLM (Need Contributors)Apr 2026 · locallllm.fly.dev · ▲16
I built localLLLM: a small community project for running local models. Live: https://locallllm.fly.dev The goal is simple: if someone has model + OS + GPU + RAM, they should get steps that actually work (ideally one liner) I need help populating and validating guides. If you run local models, please submit one working recipe (or report what failed). Would love to hear general feedback as well!
- BABuild apps with 500 models locally. No tracking, no cloud, just codeDec 2025 · github.com · ▲6
I built CodinIT because I wanted that "Bolt-like" experience, but on my own terms. 100% Open Source The core idea: You should be able to prompt a full-stack application into existence, but the environment should be local, the models should be swappable (Ollama/LM Studio support was a priority), and the output should be standard code you actually own. A few things I focused on: Context Management: One of the hardest parts was figuring out how to feed the right file context back to the LLM without blowing out the token limit. I’ve implemented a custom indexing approach to keep the "vibe…
- LALocoStudio - A better UI for Ollama2025 · locostudio.ai · ▲6
Hi HN, I’m excited to share LocoStudio (http://locostudio.ai), a local-first AI chat app for Mac that lets you chat with AI models both locally and in the cloud—all in one place. Why I built it: I wanted a private, fast, and flexible way to use the latest AI models without sending my data to the cloud. Most AI chat apps are either cloud-only (raising privacy concerns) or have clunky interfaces for local models. LocoStudio aims to make local AI chat as easy and powerful as using ChatGPT, but with your data staying on your device. What it does: - Private, local-first: Run open models…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, October 2023
the whole month →
Nudge 2.0▲1,051In-app experiences to activate, retain, & understand users
Growth · 2023 · nudgenow.com
Unlock AI magic for elevated customer engagement, fast
AI · 2023 · tiledesk.com
- OD
Effortlessly discover API behaviour with a Chrome extension that automatically generates OpenAPI specifications in real time for any app or website.
Dev tools · 2023 · github.com