We make Conversational AI private

Leverage Conversational AI without worrying about privacy. We provide end-to-end protected AI services that ensure your data stays yours, not even our admins can see it


We provide confidential AI services that leverage our open-source, independently audited, and Zero-trust architecture to ensure your data remains private.

Our security and privacy posture guarantees that not even our admins can access your data. Your data remains yours.

We cannot

see your data.

train on your data.

leak your data.

see your data.

Use cases

For developers

Speed up LLM adoption and cut costs without compromising on privacy with our Zero-trust AI API.

For AI-empowered employees

Use a data leakage risk-free AI tool to get productivity while preserving corporate confidentiality.

How we secure your data


We serve AI models in a hardened environment that ensures data is never exposed, as all external access are removed


We use secure hardware to provide cryptographic proof so that you can have irrefutable proof your data will remain confidential

Data within our API and Chat cannot be accessed by anyone, including Mithril staff… except you!

Learn more about our security

Why trust us

Our solution is open-source and can be publicly audited.

Our products have also been audited by independent security labs.

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

Supported by

Why BlindLlama?

Don’t compromise on the privacy of on-VPC deployment and the ease and cost efficiency of SaaS AI

Deployment speed
On-VPC Deployment
Regular AI APIs
Not private
Zero-trust AI APIs

import blind_llama

prompt="Write me a poem"

Ready to use zero-trust AI ?

Get started

Join the

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Join the community, share your ideas and talk with Mithril’s team.

Join the discussion

Contribute to our project, and mention open issues and PRs.

Start Contributing