Local-first bioinformatics platform
Run your own WGS at home.
Full 30X whole genome sequencing analysis in under 2 hours on your RTX 4090.
✨ Free for personal use. Your data never leaves your machine.
Analyze my whole genome sequencing data from /data/wgs using Parabricks.
Planning GPU-accelerated workflow...
Parabricks Germline → FASTQ to BAM → VCF
Built for
Built for bioinformatics
Everything you need to plan, run, and monitor computational biology workflows.
Ask in plain language. Get reproducible pipelines.
Describe your analysis goal and let the agent plan the optimal workflow. No scripting required — just scientific intent.
Learn moreWhy Bioinfoflow?
Built from the ground up for computational biology workflows.
Agentic Planning
Describe your analysis goal in plain language. The agent plans the optimal workflow, selects tools, and configures parameters.
Local-First Compute
Your data never leaves your infrastructure. Run compute-heavy workflows on your own machines or cluster.
Reproducible Artifacts
Every run stores its config, samplesheet, and environment. Re-run any analysis months later with identical results.
Real-time Observability
Watch your pipeline execute with DAG visualization, streaming logs, and resource utilization metrics.
How it works
From biological question to reproducible results in four steps.
Select Workspace
Choose your local data folder. Your files stay where they are.
Describe Intent
Tell the agent what analysis you need in plain language.
Agent Plans
AI selects the optimal workflow and generates configuration.
Run & Monitor
Execute locally with real-time DAG, logs, and results.
Select Workspace
Choose your local data folder. Your files stay where they are.
Describe Intent
Tell the agent what analysis you need in plain language.
Agent Plans
AI selects the optimal workflow and generates configuration.
Run & Monitor
Execute locally with real-time DAG, logs, and results.
What you get
Core capabilities that make bioinformatics workflows faster and more reliable.
30X WGS in < 2 Hours
Run complete whole genome sequencing analysis on your RTX 4090 at home. No cloud required.
Natural Language to Pipeline
Describe your analysis in plain English. Get a configured, ready-to-run workflow.
Zero Data Movement
Process terabytes of sequencing data without uploading. Your files stay on your infrastructure.
Full Provenance
Every run captures exact versions, parameters, and outputs. Reproduce any analysis, anytime.
Based on internal benchmarks comparing manual nf-core configuration vs. agent-assisted setup for RNA-seq workflows.
Your data, your control
Built for sensitive biological data. Run analyses without compromising security or compliance.
Data never leaves
Your files stay on your machine by default. No cloud uploads required.
Full audit trails
Every run logged with complete provenance and timestamps.
Local artifacts
Configs, samplesheets, and results stored in your workspace.
Secure by design
Built with research data compliance requirements in mind.
Your infrastructure
Run on your HPC, cloud, or local workstation.
Transparent execution
See exactly what runs, where, and how at every step.
Ready to try it?
Run your first pipeline in minutes. Free for individual researchers.