Empowering developers with privacy-first AI APIs

Integrate cutting-edge AI into your apps without compromising on security and privacy thanks to end-to-end encrypted APIs

Confidential Conversational AI API

coming soon

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

Confidential AI

We use end-to-end encryption with Confidential Computing, to enable you to benefit from AI, like conversational bot, without exposing your data.

We can’t listen to your queries as we cannot access the decryption keys. Privacy is built by design in our solution.

import blindai

blindai.api.Completion.complete ("I love AI and privacy because")

Why BlindAI ?

BlindAI provides flexible and powerful AI APIs that can be leveraged into your apps, without having to worry about security and privacy.

No infrastructure headache

We manage the infrastructure and the model, you manage the keys

Low time to value

We provide models to infuse your apps with AI in a few lines of code.

Secure and private

We process data only in secure enclaves, making it end-to-end protected and unreadable to us


Data confidentiality and privacy are guaranteed and we can provide an audit trail

Leverage AI
without insecurity


Structure messy medical recordings


Analyse customer data to detect fraudulent behavior


Build insights from customers exchanges
Use case not listed?

Privacy trough openness

BlindAI is an open-source solution using Confidential Computing to secure sensitive data analysis.

The code is publicly editable, and is being audited by an independent security lab. The audit will be publicly available soon

The model we use is OpenChatKit, an open-source cutting-edge Large Language Model developed by Together.
For AI engineer

Deploy your own models
with privacy

BlindAI allows AI engineers to deploy their own models with privacy guarantees to serve their most demanding users. You can learn to deploy it on your premise by following our documentation.
Learn more about our security

Security through transparency

The key technology we use to secure users’ data is Confidential Computing (CC), and our mission is to democratize AI through BlindAI. You can find more about CC below and how we infuse it in BlindAI.

For beginners
in Confidential Computing

Discover our advanced material for security experts

For experts
in Confidential Computing

Learn how we implemented security and privacy by design
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

Join the

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

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

Start Contributing

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

Join the discussion

Follow and contribute to our upcoming projects.

Open the roadmap