mithril-security/blind_llama_client

Zero-trust AI APIs for easy and private consumption of open-source LLMs

33
/ 100
Emerging

This project helps developers integrate open-source Large Language Models (LLMs) like Llama2 into their applications while ensuring the privacy of user data. It takes user input and securely processes it with an LLM, returning the model's output without exposing the data to the service provider. The primary users are developers building applications that need to leverage LLMs for sensitive information.

No commits in the last 6 months.

Use this if you are a developer building an application that needs to use open-source LLMs but requires strong guarantees that user data remains confidential and is not exposed to the AI service provider.

Not ideal if you are a non-technical end-user looking for a ready-to-use LLM chat interface, or if your application does not handle sensitive data that requires advanced privacy protection.

data-privacy LLM-integration secure-AI-deployment confidential-computing API-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

41

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Jul 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/mithril-security/blind_llama_client"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.