Graphomics logoGraphomicsRead the Docs
The Ground · MapForge

License the engine that builds the graph.

Point MapForge at a domain. It ingests the sources, links the entities, scores its own confidence on every connection, and serves the result through a production API — in days. You license the engine, not a static dataset someone else froze.

Read the DocsTalk to Us →

Any format. Any biological domain.

Biological data rarely arrives as a clean spreadsheet. MapForge ingests structured data regardless of format. CSV, TSV, JSON, Parquet, and SQL dumps are the common cases — not a fixed list.

CSVTSVJSONParquetSQL
Nothing ships on autopilot

Every link is scored, then reviewed.

Every entity link MapForge proposes is scored for confidence and queued for human review before it enters the graph. Illustrative example below — not live production data.

Proposed linkPending review
Faecalibacterium prausnitzii
— produces →
Butyrate
Confidence92%
Sourced from 3 references · awaiting reviewer sign-off
A production API

Not a script. An endpoint your systems can call.

RBAC & rate limits
Access control and throughput scoped per organization.
Confidence on every edge
Every connection returns its own confidence score, not just the data.
60+ endpoints
Query entities, relationships, and provenance directly.

Federation runs at the graph layer, so one query can span multiple constituent graphs with unified provenance. Microbiome is what's loaded today; more domains come online as they're built.

The worked example

MicroMap is what MapForge built first.

A microbiome knowledge graph with 1.7M+ entities, built from raw sources — not a static export. See the numbers.

See the proof →
Deployment

Runs where your data already lives.

Managed
We run it. You query it. Nothing to maintain.
Self-hosted
Deployed inside your own environment, under your controls.
Licensed
License the engine outright and run it anywhere.

Ready to build your own graph?

Read the DocsTalk to Us