Open Infrastructure · Three Audiences

Build on the evidence layer.

Whether you're writing code, designing studies, or training agents — OpenBio gives you typed, provenance-tracked, trust-layered evidence for every living system.

DevelopersResearchersClinicians

Explore the platform

For Developers

A typed SDK for every layer of the stack.

Ingest from FHIR, HL7v2, or file upload. Query evidence with trust filters. Stream structured context to your agents. Every call returns full provenance.

npm install @openbio/sdk

const client = new OpenBio({ apiKey: process.env.OPENBIO_API_KEY })

await client.ingest.fhir({
  sourceSystemId: 'epic-mount-sinai',
  bundle: fhirBundle,        // FHIR R4 Bundle
})
// → { ingestionId, assertionsCreated: 42 }

typescript

const cohort = await client.cohorts.query({
  criteria: [
    { type: 'genomic_variant', code: 'EGFR_L858R' },
    {
      type: 'lab_result',
      code: 'LOINC:718-7',
      value: { lt: 10 },   // hemoglobin < 10 g/dL
    },
  ],
  subjectTypes: ['human', 'canine'],
  trustLayers: ['source_fact', 'normalized_fact'],
})
// → { subjects: [...], matchCount: 3 }

For Researchers

Evidence queries that span species.

The same hemoglobin result in a human patient and a Golden Retriever lives in the same model. Query across both. Compare treatment responses. Build cohorts that span biology, not just systems.

For AI Agents

Evidence as structured agent context.

OpenBio doesn't give your agent a wall of text. It gives typed assertions with trust scores, provenance chains, and temporal context — exactly what LLMs need to reason about biological evidence without hallucinating.

{
  "name": "get_subject_evidence",
  "description": "Retrieve evidence assertions for a biological subject",
  "parameters": {
    "subject_id": { "type": "string" },
    "trust_layers": {
      "type": "array",
      "items": { "enum": ["source_fact", "normalized_fact", "derived_feature", "model_output"] }
    },
    "evidence_types": { "type": "array", "items": { "type": "string" } }
  }
}