Converse with AI privately

Open-source and privacy-by-design alternative to ChatGPT. Leverage the power of Conversational AI without fearing your data could be accessed or used for training.

Get started

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. At no time do we 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 auditable. We have been audited in the past on a related project BlindAI, and will be audited for BlindChat in the near future.
‍
We provide cryptographic proof that our services are built in a way where we cannot see or train models on users' data.

Check security

Our project

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 client-side computation and privacy-enhancing technologies such as remote enclaves, we provide powerful, easy-to-use private AI services.

Browse on GitHub