Iván Martínez

Founder & Co-CEO @ZylonPrivateGPT. Private AI for the Enterprise. Creator of Private GPT, 54K+ Github stars:

[Iván Martínez @ivanmartit]

Privacy is a top concern when discussing ChatGPT-like tools with professionals. With this working proof of concept, I show how open-source models and tools like @langchain enable a 100% local execution, ensuring your data never leaves your environment. https://t.co/Pq2LbBnPYJ

[Daniel Gallego @thanos_malkav]

@LinusTech needed two RTX 5090s and a full episode to run AI locally.

A bank or defense agency needs that plus deployment tooling, security accreditation and support.

@bradflora from @ycombinator just called it the air-gapped economy. That’s what we build @ZylonPrivateGPT for.

[Iván Martínez @ivanmartit]

Since 2023, first with PrivateGPT and now @ZylonPrivateGPT, we’ve been bringing AI inside those walls.

PrivateGPT: 57K GitHub stars. Zylon: running on-prem at banks, gov and defense across the US, Europe and LatAm.

If your data can’t leave the building, let’s talk.

#OwnYourAI

[Y Combinator @ycombinator]

AI for the Air-Gapped Economy
@bradflora

Some of the most valuable data in the world can never leave the building. Defense contractors, banks, hospitals, and nuclear plants can’t simply send it to a cloud AI API.

That creates an opportunity to bring frontier AI inside those walls: on-prem models, deployment tooling, security accreditation, and hardware for the parts of the economy the cloud can’t reach.

[ollama @ollama]

Big day for Ollama! When we started, open models and the open source AI ecosystem were in their early days with few believers.

Our belief in open source has never wavered.

With today's fundraising announcement and our 9M+ active builders, we’re ready to scale open models into AI that you can own.

All aboard open models!

🧵

[Iván Martínez @ivanmartit]

cc @MatthewBerman 👀 We are so back :)

[Iván Martínez @ivanmartit]

Learn how to run PrivateGPT local AI inside Microsoft Word, PowerPoint, and Excel 😎

Convenient, useful, and private. Honestly, I love it.

In case you didn't have a small side project for the weekend, now you have one 😆.

Happy to support you in our Discord channel

[Iván Martínez @ivanmartit]

Running, of course, on top of @ollama !

[Iván Martínez @ivanmartit]

Local, natural-language database querying is one of the features I enjoy most in the new PrivateGPT 1.0.

It comes ready-to-use (via API & UI), with support for MSSQL, Postgres, DB2, and MySQL.

Give it a try this weekend!

https://t.co/JTepUhDS3Z

[Zylon @ZylonPrivateGPT]

PrivateGPT is back!

In 2023, it became the first offline RAG implementation and a breakout open source project.

Then we went quiet in 2024.

Today, PrivateGPT 1.0 is here: a full application API layer for local AI.

https://t.co/Oag5ziyXEO

[Zylon @ZylonPrivateGPT]

🚀 MAJOR NEWS: Strategic partnership with @TelefonicaTech to revolutionize enterprise AI!

When one of Europe's largest tech giants validates your approach, you know the market is shifting toward private AI workspaces where data sovereignty is ensured 🔐

https://t.co/P6kzM6SvX7

[Zylon @ZylonPrivateGPT]

🫵 Join us for our next event on #PrivateAI hosted by
@GoogleStartups Madrid on June 9th at 17:00 for great talks and even greater food and drinks networking afterwards 🍻

Register now! https://t.co/0KUXSLiOqN

[Iván Martínez @ivanmartit]

Understanding MCP architectures helps teams make smarter AI integration decisions. The key factor is where the LLM processes data. This diagram different setups - no "wrong" choice if you're informed about the tradeoffs.

More details:
https://t.co/6bI0no8TI7

[Iván Martínez @ivanmartit]

@CarlesRamio @espublico Muy buen artículo @CarlesRamio. La única alternativa real es "Private AI": una AI que no utiliza la nube, sino que está 100% circunscrita al entorno seguro de la administración. Es nuestra misión en @ZylonPrivateGPT, y trabajamos en una exploración inicial con la administración.

[Zylon @ZylonPrivateGPT]

Episode 1 of our "Zylon Success Stories" series with @UCBerkeley's @GoldmanSchool who built ChatGSPP using our open-source PrivateGPT tech - a fully private #AI chatbot running on-prem that helps students & faculty access information in a quick & easy way https://t.co/BZjOTFyBtT

[Andrej Karpathy @karpathy]

https://t.co/3CR1HXfFxb

[Iván Martínez @ivanmartit]

@Mascobot @a16z Would love to test @ZylonPrivateGPT on that beast! A match made in heaven. SSH access and a couple hours is all it'd take to bring the world's most powerful on-prem AI platform into your setup. Seriously, drop me a dm if you're up to it!

[Iván Martínez @ivanmartit]

🤯 What our team at @ZylonPrivateGPT just built has shattered every boundary of on-prem enterprise AI.

Agentic workflows, real-time collaboration, editable canvas, inline AI support, multi-modality...
... 100% on YOUR servers.

No more "quality or privacy" dichotomy. 💪

[Zylon @ZylonPrivateGPT]

💪 Yesterday: "I need to do this."
🦾 Today: "I need to ask AI to do this."
🧠 Tomorrow: "I need to explain the problem to AI so it can solve it."
🤖 Near future: "I need to update AI on our company vision so it can identify and solve our next critical problems."

🗒️👇

[Zylon @ZylonPrivateGPT]

With us your company data NEVER leaves your servers, no matter what LLM we use.
Our on-prem AI runs ENTIRELY local in YOUR infrastructure with zero outbound connections.
It's not marketing—it's architecture.
True data sovereignty means complete control.

https://t.co/tTa0OgFYQN

[Sophia Yang @sophiamyang]

Announcing @MistralAI Small 3.1: multimodal, multilingual, Apache 2.0, the best model in its weight class.

💻 Lightweight: Runs on a single RTX 4090 or a Mac with 32GB RAM, perfect for on-device applications.
🗣️ Fast-Response Conversations: Ideal for virtual assistants and other applications where quick, accurate responses are essential.
⚡ Low-Latency Function Calling: Capable of rapid function execution within automated or agentic workflows.
🔍 Specialized Fine-Tuning: Customizable for specific domains.
🧠 Advanced Reasoning Foundation: Inspires community innovation, with models like DeepHermes 24B by Nous Research built on Mistral Small 3. We're releasing base and instruct checkpoints for Mistral Small 3.1 to support further downstream customization of the model.

[Nous Research @NousResearch]

Announcing the latest DeepHermes Preview models, DeepHermes 24B and 3B!

https://t.co/YQ3ne2PbkB

These new models are Hybrid Reasoners - meaning you can toggle ON and OFF the long chain of thought reasoning whenever you want a short, intuitive answer, or a long, well reasoned higher accuracy answer, now available on our API and to download on HuggingFace.