It's time to build bio: introducing the Genome API

For the last decade, the consumer genome has been locked behind apps, PDFs, and proprietary pipelines. Companies sequenced genomes, packaged the results into closed reports, and treated the underlying data as an asset to protect and monetise rather than a foundation to build on. Builders were left with whatever they were given.

This was a choice, not a constraint. We can choose differently.

Personalisation is still built on population averages. Products learn from demographics, surveys, behaviour, wearables, and laboratory results. These signals are useful, but they mostly describe what has already happened.

The genome helps explain what those averages miss: why two people can eat the same food, take the same medication, follow the same training plan, or share the same environment and respond differently. It gives every other signal individual context, so products can move from grouping similar users to understanding the person in front of them.

Today, The Genome Computer Company is opening access to the Genome API.

We handle everything from sequencing to a continuously interpreted genome, so teams can build personalised applications for every user.

Building on the genome is an infrastructure problem

A genome is not a field to add to a user profile. Building on it means coordinating collection and laboratory processing, moving large genomic files, calling and normalising variants, applying scientific evidence, tracking guideline changes, and designing outputs that are useful without overstating what genetics can say.

Those responsibilities normally live across different laboratories, bioinformatics pipelines, databases, and specialist teams. The Genome API turns them into one product surface.

What the API does

Partners can order 3x or 30x whole-genome sequencing, order GSA genotyping, or start with an existing gVCF. We handle kits, shipping, laboratory processing, conversion, and secure delivery.

Sequencing data is returned as a structured .genome/1.0 bundle, with gVCF and FASTQ deliverables available where applicable. Fresh sequencing and imported genomic data converge on the same downstream resources.

A genome can also be kept as a secure hosted resource. Hosted genomes are automatically reinterpreted as the underlying research and knowledge base change. Each interpretation remains versioned, so an application can see what changed and which evidence produced the new result.

From that hosted genome, an application can build structured panels or ask bounded plain-language questions. Outputs include evidence levels, citations, limitations, provenance, and safety metadata. Agents can query the same genome through the Genome Computer MCP server.

One genome, two useful forms

The API separates portability from ongoing interpretation rather than forcing partners to choose between them.

The portable genome. A .genome bundle is an open, durable representation of the genome built for software. It separates genomic data, interpretation, evidence, and rules into explicit, versioned structures. The person can download it, keep it, self-host it, or use it with another compatible tool.

The hosted genome.A hosted genome is a persistent API resource that is automatically reinterpreted as knowledge changes. It supports panels, bounded Q&A, interpretation history, and application access without taking portability away from the individual.

Why .genome matters

Conventional genomic files are essential inputs for bioinformatics, but they were not designed as application-layer context. A .genome/1.0 bundle makes four properties explicit.

It is structured for software. Variant data, interpretations, evidence, and rules have defined locations and meanings. Applications do not need to reconstruct a result from a loosely encoded report.

It is deterministic. Computed results are generated against pinned reference, pipeline, and evidence versions rather than guessed at the moment a question is asked.

It is queryable. Applications and agents can retrieve the relevant parts of a genome directly without loading a complete sequencing file into context.

It is versioned end to end. A future reinterpretation can be compared with the exact result and evidence snapshot that came before it.

What you can build

The API is designed for products that need genetics as one part of a broader understanding of the user. Examples include:

• Nutrition applications that incorporate inherited metabolism and dietary-response context.
• Sleep, fitness, recovery, hormone, skin, and healthy-aging experiences grounded in the user's genome.
• Medication-related genetics for clinician-facing review, with clear limits around diagnosis and dosing.
• Agents that query a deterministic genome resource through MCP rather than extracting genetics from reports.
• Research platforms that move consented genomes into governed workflows without building a separate ingestion stack.

Genetics does not replace symptoms, medical history, laboratory results, environmental factors, or clinical judgment. It adds a persistent layer of context that can make those other signals more individual.

Built for integration

Staging includes fixed synthetic genomes, synthetic orders, and deterministic panel outputs, so a team can build the complete integration without using anyone's real genomic data. The same API surface moves into production with separate credentials, data controls, consent requirements, and billing.

TypeScript and Python SDKs cover orders, uploads, hosted genomes, interpretations, panels, Q&A, webhooks, usage, and billing. Scoped keys allow each application service to receive only the access it requires.

Accredited and auditable infrastructure

Sequencing is performed through CLIA- and CAP-accredited laboratory partners in the United States. Genomic-data handling uses controlled production workflows and reproducible processing.

Every generated bundle pins:

• Pipeline and schema versions.
• Reference build.
• Evidence and annotation-source snapshots.

Results can be inspected, reproduced, challenged, and compared with later interpretations.

Individual control is part of the company structure

Genome Computer operates under Genetic Superintelligence Company, a Delaware Public Benefit Corporation. Our charter commits us to keeping identifiable individual genetic data under individual control and out of commercial sale or licensing.

This matters for an API that other companies build on. A partner can deliver a portable genome rather than creating another locked report, and the individual does not have to surrender ownership in exchange for ongoing interpretation.

Read more about our commitment as a Public Benefit Corporation.

Request access

We are working with teams building consumer, clinical-adjacent, research, and agent-based products. Tell us what you are building at genome.computer/api or write to api@genome.computer.

The genome should be a building block for software, not the endpoint of a sequencing report. It's time to build, on the genome.