Now in private preview

Your genome, read by an AI that belongs to you.

Helixstreet builds the Sovereign Twin — a private, in-cloud AI that reads your whole genome, talks to you about it, and helps you act on it. Your data never leaves a perimeter you control.

It runs inside your own Google Cloud project on Vertex AI and Gemini 2.5 Pro — no third-party training, no shared inference, no data egress.

Launch the app → See how it works Runs on Google Cloud · Vertex AI · Gemini 2.5 Pro
Scroll
Product

A digital twin that actually knows the substrate it runs on.

Whole-genome aware

Gemini's million-token context lets the twin read across your full sequence — variants, regions, and structure — in one go.

Sovereign by construction

Runs inside your own Google Cloud project on Vertex AI. No third-party training, no shared inference, no data egress.

Conversation, not a report

Ask in plain language. The twin grounds every answer in your sequence and the literature, and shows its work.

How it works

Three steps from raw sequence to a twin you can talk to.

01

Bring your genome

Upload a VCF or FASTA into a project you own. Encrypted at rest, scoped IAM, no copies anywhere else.

02

Instantiate the twin

Vertex AI provisions Gemini 2.5 Pro inside your perimeter and indexes your sequence into long-context working memory.

03

Ask anything

Pharmacogenomics, carrier status, ancestry, variant interpretation — grounded in your data with citations you can audit.

Trust

The answer to "where is my genome right now?" is always: with you.

Your cloud, your keys

Helixstreet deploys into your GCP organization. CMEK, VPC-SC, and audit logs are yours to configure.

No training on you

Vertex AI does not use your prompts or sequences to train foundation models. We don't either.

Open and auditable

Every answer traces back to a region of your sequence and a source it cites. No black boxes, no magic.

Ready to meet your twin?

Open the app, connect a project, and try a conversation. Private preview — no waitlist for the curious.

Launch the app →