DEV Community: David Simões

I Built a Private AI Assistant That Runs 100% Locally — No Cloud, No Subscriptions

David Simões — Tue, 12 May 2026 23:49:32 +0000

Every time I used ChatGPT or similar tools the same thought crossed my mind:

"Where is this conversation going? Who has access to it? What are they doing with my data?"

So I decided to build my own solution. Meet CrustAI 🦀 — a fully private, self-hosted AI assistant that runs entirely on your own machine.

No cloud. No subscriptions. No data leaving your computer. Ever.

🌐 Documentation | ⭐ GitHub

The Problem I Wanted to Solve

Most AI assistants have one fundamental issue — your data belongs to someone else.

When you ask ChatGPT something personal, that conversation is:

Stored on OpenAI's servers
Potentially used to train future models
Subject to their privacy policy (which can change)
Accessible in case of a data breach

I wanted an AI assistant that was genuinely mine — one that I could use daily through apps I already use (Telegram, WhatsApp) without worrying about privacy.

What is CrustAI?

CrustAI is a self-hosted AI assistant powered by Ollama that connects to your favorite messaging platforms and runs completely offline after setup.

Key features:

🔒 100% Private — all processing happens on your hardware
🧠 Local LLM — powered by Ollama (llama3.2, tinyllama, phi3, mistral...)
📱 Multi-platform — Telegram, WhatsApp, Discord and Slack
🧬 Long-term memory — remembers facts across conversations
🗣️ Offline voice — speech-to-text and text-to-speech (pt-BR)
⚡ REST API — built-in Fastify server for custom integrations
🎭 Custom personality — fully configurable assistant behavior

Tech Stack

Technology	Purpose
Node.js	Runtime environment
Ollama	Local LLM inference engine
node-telegram-bot-api	Telegram integration
@whiskeysockets/baileys	WhatsApp integration
discord.js	Discord integration
@slack/bolt	Slack integration
Fastify	REST API server
sql.js	Embedded SQLite for memory
yaml	Configuration management

Architecture Overview

The architecture is straightforward — a central message handler receives messages from any platform and routes them through the same pipeline:

┌─────────────────────────────────────────────────────┐
│                     CrustAI Core                     │
│                                                      │
│  ┌──────────┐  ┌──────────┐  ┌──────────────────┐  │
│  │ Telegram │  │ Discord  │  │     WhatsApp     │  │
│  │  Adapter │  │  Adapter │  │      Adapter     │  │
│  └────┬─────┘  └────┬─────┘  └────────┬─────────┘  │
│       └──────────────┼──────────────────┘            │
│                      ▼                               │
│            ┌─────────────────┐                      │
│            │  Message Handler │                      │
│            └────────┬────────┘                      │
│         ┌───────────┼───────────┐                   │
│         ▼           ▼           ▼                   │
│    ┌─────────┐ ┌────────┐ ┌──────────┐             │
│    │  Ollama │ │ Memory │ │ REST API │             │
│    │  (LLM)  │ │  Store │ │  Server  │             │
│    └─────────┘ └────────┘ └──────────┘             │
└─────────────────────────────────────────────────────┘

Each platform adapter is independent — you enable only what you need in config.yml.

Getting Started in 5 Steps

Prerequisites

Node.js ≥ 20
Ollama installed
A Telegram bot token from @BotFather

Step 1 — Clone the repository

git clone https://github.com/DaveSimoes/CrustAI.git
cd CrustAI

Step 2 — Install dependencies

npm install

Step 3 — Start Ollama and pull a model

# Start the Ollama server (keep this terminal open)
ollama serve

# In a new terminal — pull a lightweight model
ollama pull tinyllama   # 600MB — works on modest hardware
# or
ollama pull llama3.2    # 2GB — needs ~8GB RAM

Step 4 — Configure the project

cp config/config.example.yml config/config.yml

Edit config/config.yml:

model: tinyllama
ollama_url: http://localhost:11434
language: pt-BR

telegram:
  enabled: true
  token: YOUR_BOT_TOKEN_HERE
  allowed_user_ids: []

Step 5 — Launch CrustAI!

npm start

Expected output:

✓ Ollama connected     (tinyllama)
✓ Memory store ready   (./data/memory.db)
✓ Telegram ready
✓ REST API ready       (http://localhost:3000)

🦀 CrustAI is ready. Your shell awaits.

Available Commands

Once running, use these commands directly in Telegram (or any connected platform):

Command	Description
`/ping`	Check if the bot is alive
`/help`	Show all commands
`/model`	Show which AI model is running
`/remember <fact>`	Store a fact in long-term memory
`/forget`	Erase all stored facts
`/clear`	Clear conversation history

The Privacy-First Philosophy

CrustAI was built with privacy as its core principle, not an afterthought:

✅ All conversations processed locally — nothing leaves your hardware
✅ No calls to OpenAI, Anthropic, Google or any cloud AI service
✅ No telemetry or usage tracking
✅ Open source — audit every single line of code
✅ MIT license — use it however you want

Running on Modest Hardware

One concern I had was performance. I'm running CrustAI with tinyllama on a machine with limited RAM and it handles daily conversations well.

For basic Q&A and conversation, tinyllama is surprisingly capable. If you have more resources, llama3.2 or phi3 give significantly better results.

What's Next — Roadmap

[ ] Web UI dashboard
[ ] Image understanding (multimodal LLMs)
[ ] Plugin system for custom tools
[ ] Docker one-click deployment
[ ] Mobile app companion

Contribute!

CrustAI is open source and I'd love contributions from the community:

🐛 Bug reports — open an issue
💡 Feature ideas — let's discuss in issues
🔧 Pull requests — always welcome
⭐ Star the repo — helps others discover it!

GitHub: https://github.com/DaveSimoes/CrustAI
Documentation: https://documentcrustai.netlify.app

Final Thoughts

Building CrustAI taught me a lot about local LLM inference, multi-platform bot development, and the real meaning of privacy-first software.

If you're tired of sending your conversations to the cloud, give CrustAI a try. Your data deserves to stay yours.

Made with 🦀 and ❤️ by Dave Simoes

If you found this useful, consider starring the repo and sharing with others who care about privacy!

How I Built a Privacy-First AI Assistant That Runs 100% Locally with Node.js and Ollama

David Simões — Thu, 07 May 2026 22:57:42 +0000

Most AI assistants today depend heavily on the cloud. Your data leaves your device, goes to external servers, and you depend on third-party APIs.

I wanted to explore a different approach.

So I built CrustAI — a self-hosted AI assistant that runs entirely on your machine, powered by local LLMs through Ollama, and integrated in real time with Telegram, WhatsApp, Discord and Slack.

Key ideas behind the project:

Total privacy (no data leaves your machine)
Real-time messaging integrations
Long-term memory between conversations
Offline speech-to-text and text-to-speech
Extensible Node.js architecture with REST API

This is not theoretical. You can clone the repo and run it today.

GitHub repository:
https://github.com/DaveSimoes/CrustAI

I’d love to hear thoughts from the community.

Building VercelZero: An Open-Source Deployment Platform Experience with Next.js + AI

David Simões — Sat, 14 Mar 2026 04:41:20 +0000

I’ve been working on VercelZero, an open-source project inspired by the original Vercel platform experience.

The main objective is to create a portfolio-grade, community-friendly codebase that demonstrates:

product-oriented frontend engineering,
scalable component architecture,
realistic deployment-style UX,
and AI-assisted user interactions.

What’s inside:

Simulated deployment flow for frontend projects
Preview-oriented interface
Dashboard-centric experience
Responsive UI

Stack:

Next.js 14
TypeScript
React 18
Tailwind CSS
CopilotKit / OpenAI integration

Why I’m sharing this
I want this repository to be useful for:

developers learning modern SaaS-like frontend patterns,
contributors looking for a clean open-source project,
and recruiters evaluating technical depth + product thinking.

If this project is helpful, feel free to:

⭐ star the repository,

🐛 open issues with suggestions,

🔀 submit pull requests.

I’d love your feedback and ideas for the roadmap.

[https://github.com/DaveSimoes/VercelZero]

Crie um modelo de interface Login / Sign Up (UI) em React utilizando Bootstrap 5

David Simões — Sat, 02 Sep 2023 01:54:59 +0000

Introdução:
Olá Família Devs.
Neste tutorial vamos aprender a criar do zero uma interface de Login / Sign Up utilizando React e Bootstrap 5 .

Acredito que o entendimento inicial deste simples modelo irá ajudar a compreender alguns rudimentos que poderão te levar a escalar projetos acrescidos com backend, onde vc poderá se conectar por exemplo a BD´s SQL (Oracle, MySQL, Microsoft SQL Server, PostgreSQL) ou NoSQL (MongoDB, Amazon DynamoDB , entre outros.)

Em breve estaremos publicando um tutorial a respeito da parte de backend em que iremos adicionar neste projeto.

Porém por agora, para facilitar a fixação de todas as etapas de construção do sistema, vamos focar apenas no FrontEnd.

Então chega de conversa e mão na massa...

Índice:
1) Pré-requistos;
2) Configuração da biblioteca React;
3) Instalação e configuração do framework Bootstrap;
4) Criação dos componentes Login e Signup;
5) Ativação do Routing no React;
6) Criar modelo de interface de usuário (UI Template) de login, utilizando o Bootstrap;
7) Criação do modelo de UI de cadastro React com Bootstrap;
8) Criação do React Sign Up UI Template com Bootstrap
9) Adicionar estilos aos componentes de autenticação;
10) Palavras finais.

1) Pré-requistos:

Para começarmos precisamos compreender os pré requisitos para essa construção:

Para um melhor entendimento é importante ter conhecimentos básicos de HTML, CSS, JavaScript, React e uma pitada de ES6.
Verifique se você possui o Node configurado em sua máquina;

2) Configuração da biblioteca React

Execute o comando abaixo para instalar o projeto React e construir o modelo de UI do React Login-Sign Up usando create-react-app

Entre no projeto login-signup-ui

Obs: Para aqueles que estão começando, recomendo NÃO copiarem e colarem os códigos, mas visualizarem todas as imagens dos códigos que serão anexadas e busquem reproduzir as linhas de código, digitando-as. Isso forçará a se lembrarem das linhas, nomes e sintaxes necessárias na hora de digitarem.

3) Instalação e configuração do framework Bootstrap

Em seguida, abra o seu painel e instale a estrutura de UI Bootstrap este fornece ótimos componentes de UI que iremos utilizar.

Em seguida, importe bootstrap.min.css de node_modules dentro do arquivo src/App.js

4) Criação dos componentes Login e Signup

Agora é hora de criar os componentes Login e Sign up no React App;
Primeiro crie um diretório components na pasta src. E dentro deste crie os arquivos login.js e signup.js

Adicione o seguinte código no arquivo login.js.

Agora adicione o seguinte código no arquivo signup.js

5) Ativação do Routing no React

Execute o comando no terminal para instalar o módulo react-router-dom e habiliatr o serviço Router no React.

Em seguida, vá para o arquivo src/index.js e insira o seguinte código no arquivo conforme abaixo.

Imagem do arquivo src/index.js

Em seguida, importe BrowserRouter as Router, Routes, Route, Link React para habilitar os routers.

Agora entre em src/App.js e inclua o seguinte código nele:

7) Crie um modelo de UI para cadastro React com Bootstrap

A seguir, adicionaremos o seguinte código dentro do arquivo components/login.js para construir login form template

A seguir a saída para o form da UI de registro no React.

8) Criação do React Sign Up UI Template com Bootstrap

A seguir, iremos inserir o seguinte código dentro do arquivo components/signup.js para construir Sign up form template UI

Essa será a saída para o registration UI form no React.

9) Adicionar estilos aos componentes de autenticação

Nesta etapa, adicionaremos estilo ao nosso aplicativo de UI de login React para torná-lo mais atraente.

Vá para o arquivo src/index.css e adicione o código fornecido abaixo.

Você deve iniciar o aplicativo React usando o comando abaixo:

10) Palavras finais.

Por fim, construímos o modelo React Login & Sign Up UI usando a estrutura Bootstrap UI.

Espero de verdade que este humilde tutorial te ajude a entender em como usar os componentes da UI do Bootstrap para criar belos componentes no React.

Por favor, considere compartilhar com outras pessoas.

Este projeto se encontra em meu Repositório no GitHub