Is my workspace data encrypted before leaving my machine?

Yes. The Privatemode proxy runs locally and encrypts all data before it leaves your machine. It also performs remote attestation to verify the integrity of the Privatemode service, ensuring end-to-end protection for every request.

Does Privatemode store or retain data from my workspaces?

No. Privatemode is designed to never learn from your data. All inference requests are processed confidentially using confidential computing, and no documents, prompts, or responses are retained after processing.

Do all AnythingLLM features work with Privatemode?

Yes. Chat, RAG document retrieval, agents, and any other feature that uses the configured LLM provider will route through Privatemode. The embedding model can also be configured to use Privatemode's OpenAI-compatible endpoint.

How does encrypted inference affect performance?

Privatemode uses confidential computing hardware to minimize overhead. The local proxy adds only milliseconds for encryption and attestation, so response times are comparable to standard cloud AI services while providing full data protection.

Integrating Privatemode AI with AnythingLLM

AnythingLLM turns documents into AI-powered workspaces, but cloud LLM providers see every query in plaintext. Privatemode encrypts all workspace data end-to-end while giving you access to state-of-the-art models.

Introduction

AnythingLLM integration

Benefits

Why integrating AnythingLLM

Introduction

Use cloud AI in AnythingLLM without exposing your workspace data

Screenshot of Anything LLM with Privatemode

AI workspaces need powerful models

AnythingLLM lets you build custom AI workspaces for document Q&A, agents, and RAG. Cloud LLM providers deliver the best results, but they process your documents and queries in plaintext. For sensitive business data, that's a dealbreaker.

Encrypted document interaction

Privatemode provides an OpenAI-compatible endpoint that AnythingLLM connects to via the Generic OpenAI provider. Every document chunk, embedding, and chat message is encrypted end-to-end. The AI provider never sees your workspace data in plaintext.

Hardware-enforced, not only policy-enforced

Based on confidential computing, Privatemode processes your data inside a hardware-enforced enclave. This is verifiable through remote attestation and open-source code, going beyond standard cloud providers' privacy policies.

Benefits

Why use Privatemode AI with AnythingLLM?

End-to-end encrypted workspace AI

Integrating Privatemode into AnythingLLM brings cloud-AI capabilities to your document workspaces while keeping your data confidential. Every query, document chunk, and agent action is encrypted through end-to-end encryption and confidential computing. Privatemode never learns from your data.

State-of-the-art model selection

With Privatemode, you can choose from state-of-the-art LLMs to power AnythingLLM's chat, RAG, and agent features, all running confidentially inside hardware-enforced enclaves.

Native Generic OpenAI support

AnythingLLM has built-in support for custom OpenAI-compatible providers via the Generic OpenAI option. Set the Base URL to your Privatemode proxy and all workspace features work instantly, no plugins needed.

How to get started

How to set up Privatemode in AnythingLLM

Get your API key

If you don't have a Privatemode API key yet, you can generate one for free here.

docker run -p 8080:8080 ghcr.io/edgelesssys/privatemode/privatemode-proxy:latest --apiKey <your-api-key>

Run the Privatemode proxy

The proxy verifies the integrity of the Privatemode service using confidential computing-based remote attestation. The proxy also encrypts all data before sending and decrypts data it receives.

Set up AnythingLLM

Download AnythingLLM from the official website and open the application on your computer.

Configure AnythingLLM to use Privatemode

FAQ

Frequently asked questions about using Privatemode with AnythingLLM

No. AnythingLLM supports custom OpenAI-compatible endpoints natively via the Generic OpenAI provider. You set the Base URL to your Privatemode proxy endpoint and enter the model name. All workspace features, including chat, RAG, and agents, work automatically.