Get This Tool
Genomi
Pricing
- Model
- Free
Summary
Most genomic tools hand you a static PDF report and call it done — no follow-up questions, no cross-referencing, no way to drill into the evidence behind a single rsID. Genomi is an open-source AI agent harness that turns a local genomic database into a live, queryable conversation layer.
The core workflow is four steps: install the agent harness, point it at your raw genome file on disk, build a local SQLite index, then ask questions through whichever AI agent you already run — Claude Code, Cursor, Gemini CLI, Goose, and others are listed as compatible. Pharmacogenomics, carrier status, polygenic risk scores, nutrigenomics, and ancestry PCA projection are all covered through distinct skill modules backed by ClinVar, PharmCAT, PGS Catalog, HPO, GenCC, and 1000 Genomes reference data. The privacy architecture is explicit: raw genome data stays on disk, and only the specific evidence snippets relevant to a query cross the boundary to whatever LLM handles the response. The vendor marks this as experimental and not for clinical use — which means researchers and privacy-conscious individuals exploring personal data are the intended audience, not clinical teams expecting diagnostic-grade output.
Bottom line: Genomi is the right choice when a genomics researcher wants to query their own VCF against ClinVar and PharmCAT without uploading a byte — and the wrong choice the moment a team needs clinically validated output, a hosted API, or an interface that doesn't require configuring an agent harness from source.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Local-first data architecture keeps the raw genome file on disk and only sends queried evidence snippets to the LLM, so teams with strict data policies can explore personal genomic data without uploading a single variant to a third-party server.
- Skill modules cover pharmacogenomics via PharmCAT and ClinPGx, carrier status via ClinVar and HPO, polygenic risk via PGS Catalog, and ancestry via 1000 Genomes PCA — so a researcher doesn't have to stitch together five separate tools and manually reconcile their outputs.
- Each answer carries source attribution and stated evidence limits, which means you can trace a finding back to ClinVar or GenCC rather than accepting a response with no provenance — a real gap in generic LLM genomic Q&A.
- Agent-agnostic MCP and skills-host architecture plugs into whichever AI agent a team already runs, so there is no forced migration to a new interface or locked-in model provider.
- Apache-2.0 open-source license with self-hosted deployment means developers building agent-based genomic analysis tools can inspect, modify, and extend the skill layer without negotiating commercial terms.
Cons
Sign in to edit- Installation requires following a source-code setup guide and configuring an AI agent to connect to the harness — non-technical users hit a wall before they ask a single question, and there is no hosted web interface to fall back on.
- The project is vendor-labeled experimental, which means skill coverage, reference database freshness, and edge-case handling are not production-guaranteed; teams relying on consistent outputs for any regulated or clinical-adjacent workflow will find the absence of validation documentation disqualifying and will move to a certified clinical genomics platform instead.
- There is no hosted API, so teams building products that need to serve genomic queries to end users must provision and maintain their own infrastructure — at scale, that maintenance burden is not accounted for in the zero-cost licensing.
- Evidence snippets sent to an external LLM during a query still cross a data boundary, even if the raw genome file stays local; teams operating under strict genomic data agreements need to verify that snippet-level transmission satisfies their compliance posture before deploying, and the tool provides no compliance documentation to support that review.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Linux, macOS, Windows (Python-based)
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-06-09T11:29:35.161Z
Best For
Who it's for
- Genomics researchers wanting AI-powered interpretations of personal genomes
- Privacy-conscious individuals exploring their own genetic data
- Educational exploration of genomic variant interpretation
- Developers building agent-based genomic analysis tools
- Bioinformatics workflows requiring evidence-backed genetic queries
What it does well
- Understanding personal pharmacogenomics and drug metabolism
- Assessing carrier status for genetic conditions
- Exploring nutrient response and dietary tolerance based on genetics
- Calculating polygenic risk scores for disease susceptibility
- Investigating ancestry and population genetics with reference samples
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Genomi
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Genomi free?
- Yes — Genomi is fully free to use. There is no paid tier.
- Is Genomi open source?
- Yes. Genomi is open source.
- Can I self-host Genomi?
- Yes. Genomi supports self-hosting on your own infrastructure.
- When was Genomi released?
- Genomi was first released in 2024.
- What platforms does Genomi support?
- Genomi is available on: Linux, macOS, Windows (Python-based).
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Genetic data has always been easy to collect and hard to actually interrogate. Genomi addresses the gap between having a raw VCF and getting answers to specific questions — why does this drug metabolize differently, do I carry this variant, what does my polygenic risk score mean — by acting as an agent harness that exposes genomic databases as queryable tools. The installation process follows a documented INSTALL_FOR_AGENTS.md, after which the tool builds an Active Genome Index as a local SQLite database from your genome source. From there, any compatible AI agent can route questions through Genomi’s skill modules, which dispatch to validated tools covering pharmacogenomics, monogenic carrier status, nutrigenomics, polygenic risk scoring, sequence region analysis, and population ancestry.
The differentiating architectural choice is the local-first data model. The raw genome file — the vendor cites a sample of over four million variants — never leaves the machine. Only the specific evidence snippets relevant to a given query are passed to the external LLM. The docs note that teams with strict data-retention requirements can route those snippets through a local model entirely, closing the data boundary. This is not a privacy claim backed by a legal certification; it is an architectural property of how the tool is built.
Genomi fits squarely in research and informational use. The vendor explicitly labels the project experimental and states it is not for clinical use and not a diagnostic device. That boundary matters: the tool is designed for genomics researchers, privacy-conscious individuals, and developers building agent-based genomic analysis tools — not for clinical workflows where output needs to meet regulatory or diagnostic standards. The MCP and skills-host architecture means developers can extend it, but the base installation requires comfort with source-code setup and agent configuration, which rules out non-technical users without developer support.
On the integration side, the tool is described as compatible with Claude Code, Cline, Goose, Cursor, Gemini CLI, OpenClaw, Hermes Agent, and Codex. There is no hosted API — the tool is self-hosted only, installed from the GitHub repository under an Apache-2.0 license. Reference libraries stored under GENOMI_HOME include ClinVar, HPO, GenCC, PharmCAT, PGxDB, PGS Catalog, and 1000 Genomes data for ancestry PCA projection.