Privatemode
Confidential-computing inference API and chat app that serves open models through vLLM inside attested enclaves.
0 members list Privatemode, unchanged over the last 12 weeks, data as of 16 November 2026
Members who list Privatemode in their Stack, by week.
Members who list Privatemode
Be the first to add Privatemode
Nobody on Stackness runs Privatemode yet. Add it to your stack and you're the first member running it.
About Privatemode
Privatemode is a confidential-computing inference API and chat application that serves open-source AI models through vLLM within attested enclaves. Developers use it to run large language models while keeping data encrypted end-to-end, including during processing. The service encrypts data before it leaves the user's device and maintains protection throughout AI inference, with hardware-based certificates that verify the integrity of the backend.
Privatemode is developed by edgelesssys and written in Go. It offers usage-based pricing and can be deployed in minutes. The service is designed for organizations in regulated industries such as insurance, healthcare, legal services, and the public sector where data protection and compliance requirements are strict. Privatemode's confidential-computing foundation provides verifiable security guarantees backed by external audits, distinguishing it from conventional cloud AI services that process data in plaintext.
Checked 11 November 2026.
Nobody on Stackness runs Privatemode yet.
Sign up and add itPosts about Privatemode
- Do you need Jev? Typed decisions from an ordinary LLM with one token and logprobs
You can get Jev-style typed decisions from an ordinary LLM by forcing one output token and reading its logprobs. Where that matches Jev, and where it loses.