Sovereign AI that works in production

SOVEREIGN AI INFRASTRUCTURE

The operating system for your AI agents.

From the desktop to the data center, under your control.

Autonomous agents with deterministic RAG on infrastructure you control: from a 16 GB machine, designed to scale to NVIDIA GPU clusters. With local models, no sensitive data leaves your network.

10,000+automated tests

40+modules

SAST + SCAindependent external review

12+ yearsin critical systems

Measured in September 2026

IS IT FOR YOU?

“I want to use AI with my documents and customer data, but I can't send them to a third-party cloud.”

If this sounds familiar, we can help.

Book a 20-minute demo

No commitment · We reply in less than 24 hours

THE SAME PLATFORM ACROSS THE WHOLE RANGECPU → NVIDIA GPU

The runtime reserves about 8 GB. Start with 16 GB: a fast text agent. Voice and long reasoning from 32 and 64 GB.

16 GB · CPU

Recommended minimum, one machine

32–64 GB · CPU

Department-wide operation

GPU server

High concurrency

NVIDIA cluster

Large models and mixture of experts

WHAT WE ARE BUILDING

One core, two products.

Everything starts from the same principle: your information stays with you. On that core we build tools to work better.

PREVIEW · 3 NOV

Fararoni OS

The agent runtime that runs on your server, with a web interface, WhatsApp and Telegram. Early access from 3 November.

Learn more →
IN PROGRESS

Fararoni CRM

A CRM that fits your size, and your budget.

SHARED

You pay for what you use. If nobody logs in, it shuts itself down.

DEDICATED

Your own instance, just for you. Nothing shared.

Let me know when it ships →

FARARONI OS · HOW TO START

From the open core to production.

OPEN SOURCE · APACHE 2.0

Fararoni Core

Available since March 2026 · published as C-FARARONI

Fararoni's original core: the agent engine in your terminal, with no graphical interface. For learning, experimenting and building on top.

EARLY ACCESS · 3 NOV

Fararoni OS · Pilot program

Limited spots · selection by application

Try the complete platform in your company before launch: web interface, WhatsApp and Telegram, with direct support from our team.

BUSINESS

Fararoni OS Enterprise

For production

A version redesigned for production: hardened modules, with code and dependencies reviewed by an independent security provider (SAST and SCA), with support to install it on your network.

HOW IT WORKS

Local, governed and auditable.

SOVEREIGN

Your information stays in

Reasoning happens inside your network. You decide where models and data live.

CONNECTED

Where you already are

WhatsApp, Telegram, Discord and your internal systems, connected to the same agent.

GOVERNED

Nothing happens unchecked

Every action is recorded, and a person approves what matters.

MODELS · DATA SOVEREIGNTY

Your models, on your infrastructure. The public cloud, only if you want it.

You choose where each agent runs: on open models under your control, or with the cloud provider you already use. Mix them and switch anytime, without rewriting your agents.

FULL CONTROL · LOCAL

FOR SENSITIVE DATA

Open models under your control

On your machine or server, even without internet, or in your private cloud. These models are already validated in real use; you can add other compatible ones, like a self-hosted Kimi, and assign them any role.

MODELROLE IN FARARONISIZEFROM
Qwen3.5 9BRabbit · fast answers6.6 GB16 GB
Qwen3 30B InstructVoice · spoken conversation18.6 GB32 GB
Qwen3 4B InstructSummaries for voice2.5 GB32 GB
Qwen3.8 27BTortoise · long reasoning31.7 GB64 GB

GROWS WITH YOUR HARDWARE

16 GBFast text agent
32 GB+ voice
64 GB+ long reasoning
GPUeverything at once

Via Ollama or another compatible server, such as NVIDIA NIM or vLLM. Estimated memory: 8 GB runtime plus the models in use.

FASTEST · CLOUD

WITH YOUR API KEY

Public providers

Running in minutes, no hardware needed. Great for getting started or for tasks without sensitive data.

PROVIDERREFERENCE MODELSTATUS
Anthropic ClaudeClaude Sonnet 5 ● Verified in real use
OpenAIGPT-5.1 ● Verified in real use
Google GeminiGemini 3.5 Flash ● Verified in real use
DeepSeekDeepSeek V4 Flash ● Verified in real use
Kimi · MoonshotKimi K2.7 Code ● Verified in real use
Qwen · Alibaba
Token PlanQwen3.7 Plus● Verified in real use

Includes 12 models for agents.

QWENqwen3.6-flashqwen3.7-plusqwen3.7-maxqwen3.8-flashqwen3.8-maxqwen3.8-max-preview
DEEPSEEKdeepseek-v4-flash-0731deepseek-v4.1-flashdeepseek-v4-prodeepseek-v4-pro-0813
GLMglm-5.2glm-5.3
DashScope (API)Qwen3.7 Plus○ Compatible
GLM · ZhipuGLM-5.1 ○ Compatible
Microsoft FoundryKimi K3○ On request
Amazon BedrockKimi K3○ On request

For companies already on Azure or AWS: Kimi K3 is contracted through your own account, without using Moonshot's API. We integrate it if your project needs it.

Any OpenAI-compatible provider can be added without changing code.

Measured in September 2026. The brands mentioned belong to their respective owners; Fararoni is not affiliated with them.

LEARN

Just getting started with AI?

What it is, what it cannot do and why it sometimes makes things up. Explained in Spanish, without jargon.

See the guide →

NEXT STEP

Book a demo

In person in Veracruz–Boca del Río and Mexico City, or online from anywhere.
We show you Fararoni running offline, on hardware like yours.

DEMO · FREE

30 to 45 minutes

With our team and sample data. You see the AI answering with no connection.

ALREADY HAVE A USE CASE?

1 to 2 week assessment

We define what to solve, with which hardware and how long it takes. You leave with a concrete proposal.

For pilot program companies, the assessment is free.

CONTACT

Talk to Fararoni.

The same agent answers you on both channels. If you would rather talk to a person, write to us at contacto@fararoni.dev.

QR code to open the agent on WhatsApp

WHATSAPP

For your business

Tell it what you want to automate.

QR code to open the agent on Telegram

TELEGRAM

For developers

Architecture, open source and technical tests.

These are demo channels: messages go through WhatsApp and Telegram servers, so do not share confidential information. In your company, Fararoni runs inside your own network. Privacy notice.