AI Infrastructure for Life Science Agents
Genomics databases, search indexes, and research environments, purpose built for the AI world.
Rafflesia brings you the fastest homology search.
We achieve that by separating storage and compute. Sequencing databases are indexed on cheap object storage infrastructure, cached in NVMe for fast warm-cached queries, and expensive Smith-Waterman dynamic programming alignment is performed only on the subset of data that's the most relevant.
This allows us to achieve tree-of-life scale protein alignment in seconds, with an accuracy far superior to BLAST, MMseqs2 and DIAMOND.
We provide search across UniProt, PDB, and AlphaFold DB (200M+ structures), with a simple, plug-and-play, agent-ready API.
If you want to perform homology searches on your own internal databases, contact us.
Scale
Disaggregated infrastructure lets databases scale horizontally: careful indexing and an efficient query engine separate storage from compute, so each scales on its own, enabling petabyte-scale search at a fraction of the usual cost.
The approach was pioneered in the 2010s by the engineers behind Google's Dremel and BigQuery, to run SQL queries over petabytes of data. It now powers the most scalable databases on the web: Snowflake, Databricks, turbopuffer, ClickHouse, and more.
Testimonials
“Rafflesia gave us infrastructure that used to be the hallmark of large research labs.”
“1000× faster homology search unlocks entirely new research ideas that were inaccessible with MMseqs2.”
“The way we do research is changing fast with AI, and Rafflesia has become one of the primitives we rely on.”
Security
Rafflesia is trusted by bioinformatics researchers, fast-growing biotech startups, pharma companies, and frontier AI labs. Our core infrastructure was built to comply with high standards of security, compliance, and privacy.
- Audit logs
- Granular access controls
- Single-tenant or BYOC deployments
- SOC 1 Type 2 & SOC 2 Type 2 + HIPAA compliance (Pending)
- HIPAA Business Associate Agreements available on all plans
Learn more about our security and compliance practices in the privacy policy.
Team
Agentic research is the new frontier in the life sciences. Given the right tools, autonomous agents can run experiments, test hypotheses, and reason over data at a pace no human could sustain by hand, compressing centuries of discovery into years.
We're a small and mighty team of infrastructure engineers, statistical physicists, and bioinformaticians. We're building the foundational cloud infrastructure that these research agents run on, and we'd love for you to help us build it. Join us.