Introduction
Solrouter is a private AI layer for Solana. Your prompt is encrypted on your device, and the Solrouter backend never sees it in plaintext.
Solrouter is a private AI layer for Solana. On the encrypted path, your prompt is encrypted on your device, stays encrypted through the Solrouter backend, and is decrypted only inside a hardware-isolated enclave. The backend never sees it in plaintext.
In words
- A typical AI API reads your prompt as plain text on its own server.
- With Solrouter, your device encrypts the prompt first. The backend relays ciphertext and never sees the words.
- Only the enclave holds the key. It runs the model on a Nosana GPU node, then encrypts the reply so only your device can read it.
No third-party model providers
Private inference runs only on self-hosted, open-weight models on the Nosana GPU network. Solrouter does not send your prompt to OpenAI, Anthropic, or Google. The Nosana node that runs the model sees the prompt during inference, and Solrouter does not control that hardware.
Choose your surface
Use the chat app
Chat in the browser. No code. Turn on Maximum Privacy Mode to encrypt each prompt.
Build on the API
Add encrypted AI to your app or agent with the SDK, the MCP server, or the REST API.
See how it works
The enclave, encryption, attestation, and the on-chain proof, each with the code.
Check a reply yourself
Paste a lock link and watch the verification pass in your browser.
New to the tech? Start with What is a TEE? and What is private here.