Converse with AI privately

Leverage the power of Conversational AI without fearing your data could be accessed or used for training.

We are supported by OpenAI Cybersecurity Grant Program to build Confidential AI Tooling.
Learn more

We cannot see your data.

Confidential AI Assistant
Confidential AI Assistant
Code understanding
Medical notes structuration
Assisted patent writing
What our clients say

"Sometimes cryptographic techniques allow us to have our cake and eat it too. With hardware-backed compute governance we can hope to protect the privacy of AI users, the intellectual property of AI developers, and the public interest by preventing misuse — all at the same time. We are very excited to be working with the experts at Mithril to try to make this happen."

- Anthony Aguirre, Executive Director of Future of Life Institute

View customer story
What our clients say

"Mithril Security appears to offer a solution to the privacy issues that come with creating AI-assisted tools for clinicians in areas such as the NHS."

- CEO of Stealth healthcare AI startup

What our clients say

"By using BlindBox, we can now leverage LLMs to help investigators and reviewers analyze documents and speed up investigations."

- CEO of Avian Digital forensics

View customer story
What our clients say

"Mithril Security provided a way to deploy our model on-premise while ensuring our IP was protected thanks to their secure enclaves"

- Louis Combaldieu, CTO of Auxlia, editor of an AI to detect dangerous objects at airports

What our clients say

"Mithril Security confidential Al seemed one obvious choice to develop our Zero Trust search solution"

- Thierry Leblond, CEO of Scille, editor of PARSEC.
A zero trust & zero knowledge solution for sharing sensitive data on the Cloud

Privacy-first AI

Mithril Security designs products to provide AI services while ensuring users' data remains private and is neither collected nor collectible by our organization.
We employ state-of-the-art security to guarantee prompts sent to our Conversational AI remain private. We do not store prompts sent to the Conversational AI, nor do we see them or train AI models on them.

We say what we do
We are committed to :
-  Never use your data for training purposes

-  Keeping your data private and not sharing it with anyone else

-  Implementing state-of-the-art security measures 
Read Privacy policy
We do what we say
Our project is open-source and publicly auditable. Our Confidential AI solution has been successfully audited by independent experts.
We provide  cryptographic proof that our services are built in a way where we cannot see or train models on users' data.
Check security
Embrace AI without privacy concerns
BlindChat is an open-source project that aims to democratize privacy-first Conversational AI.

We architect our solution to be privacy-by-design. By leveraging privacy-enhancing technologies such as remote enclaves, we provide powerful, easy-to-use private AI services.

Lightweight Experience

Eliminate bandwidth and computing issues with our fully managed model.

Optimal Performance

BlindChat provides GPT3.5-level AI, like Llama 2 70B, with guaranteed privacy.

High Privacy

Remote enclaves in BlindChat keep your data completely private, unseen by even our admins.

Coming soon

AI Hallucination Dectection

Identify inconsistencies in AI-generated responses [Register here].

Private document search

Upload and query documents with RAG [Register here].

Read our blog

Join the community
Contribute to our project by opening issues and PRs.
Join the community, share your ideas, and talk with Mithril’s team.
Join the discussion
Contact us
We are happy to answer any questions you may have, and welcome suggestions.
Contact us