Public data federation on Gyri combines installable seeded catalogs (trials, papers, OT entity rollups, SEC filings, DailyMed) with live keyless HTTP APIs (arXiv, Internet Archive, EIA, USWTDB, CDC, EPA, NASA, and more) — joinable to CRM and comms via multihop GraphQL where interconnect keys exist.
74+ installable public data sources — seeded mirrors, Open Targets rollups, live HTTP APIs, and interconnect keys. Enable federation packs in Settings, then browse domains and see where each source cross-federates.
Related: Gyri Science · Knowledge graph for AI · Native integrations · Federated search guide
| gyri. | ||||
|---|---|---|---|---|
| Typed entity joins | ● | ○ | ◐ | ● |
| Live API multihop | ● | ◐ | ○ | ◐ |
| Seeded public mirrors | ● | ○ | ◐ | ◐ |
| Join private stack | ● | ○ | ○ | ○ |
| Cited source hydration | ● | ◐ | ● | ● |
| Cross-domain breadth | ● | ● | ◐ | ○ |
Hover any score for rationale. ● strong · ◐ partial · ○ gap · Perplexity deep dive · Biomedical federation · 53-platform landscape →
Every source below lists the other domains it multihops into via typed keys, live federators, or entity rollups — not keyword overlap.
580k+ trials, OpenAlex, and PubMed — the literature and NCT spine.
Open Targets 26.03 rollups on drugs, proteins, and diseases.
SEC section FTS, FDA labels, OpenFDA, and federal awards.
arXiv, Internet Archive, Wayback, and fatcat on the scholarly spine.
GLEIF, Wikidata, registries, and public engineering context.
USWTDB → EIA → SEC multihop — the flagship live chain.
Launch schedules, orbital elements, and NEO catalogs.
CDC, EPA, FAA, Open-Meteo, and OpenStreetMap endpoints.
DOI, NCT, CIK, ChEMBL, UniProt, and Wikidata QID keys.
Papers, trials, authors, and citation edges — install the scholarly pack for seeded mirrors plus live OpenAlex merge on every biomedSearch.
6 sources in this domain
Open Targets 26.03 rollups on 22k drugs, 19k proteins, and 28k diseases — GWAS, ClinVar, PharmGKB, expression, and ChEMBL bioactivity in one catalog.
24 sources in this domain
SEC EDGAR item-level FTS, FDA DailyMed SPL sections, OpenFDA FAERS rollups, Federal Register, USAspending, and sponsor ↔ trial joins via CIK and NCT.
9 sources in this domain
arXiv preprints, Internet Archive texts, Wayback CDX, and fatcat releases — install the open archives pack to normalize preprints on the scholarly spine.
4 sources in this domain
GLEIF, Wikidata, SAM.gov, GitHub, npm, OpenCorporates, OpenSanctions, ProPublica nonprofits, and UK Companies House — entity and registry context.
9 sources in this domain
Keyless HTTP multihop — USWTDB → EIA → SEC operator filings is the flagship chain. Optional Google Patents SERP when configured.
4 sources in this domain
Live launch schedules, NORAD orbital elements, and NEO catalogs — bridgeable to pad weather, provider identity, and public filings via coordinates and agency names.
3 sources in this domain
CDC, EPA CAMPD & FRS, FAA airports, NHTSA, Open-Meteo, Overpass, Nominatim, and USDA FoodData — installable public geo and health HTTP connectors.
9 sources in this domain
Shared keys join domains — not keyword overlap. Agents traverse DOI, NCT, CIK, ChEMBL, UniProt, and Wikidata QID in one GraphQL hop chain.
6 sources in this domain
Gyri maintains a massive public data seed in Postgres — not a one-off export you rebuild each quarter. Papers, trials, SEC filings, and typed entities index for full-text search, biomedSearch, and secFilingSearch from day one. Live API federators merge fresh hits and passively ingest them back into the mirror.
Join public entities to CRM, email, Slack, and docs. 145 native connectors ship today; HubSpot, Salesforce, Notion, Linear, and more are on the build queue.
biomedSearch → sponsor → secFilings
secFilingSearch(query: "pipeline risk") → cited sections
USWTDB → EIA plant → SEC operator (live multihop)
See the Science page for biomedical depth · How Gyri works for federation architecture
Free trial — install public data packs, live federators, and cited answers joined to your stack.
Gyri ships 74+ installable public sources: ClinicalTrials.gov (580k+ mirror), OpenAlex, PubMed, Open Targets rollups, SEC EDGAR with section FTS, FDA DailyMed, arXiv, Internet Archive, EIA, USWTDB, CDC, EPA, FAA, Open-Meteo, OpenStreetMap, NASA/CelesTrak/Launch Library live APIs, and optional Google Scholar/Patents SERP. Enable packs in Settings → Public data.
The public seed is a pre-loaded Postgres catalog you install into your workspace — papers, trials, filings, and entities indexed for full-text and graph search. Live API calls merge with the mirror and passively ingest new hits.
Yes. Multihop GraphQL links public entities (sponsors, CIKs, NCT IDs) to Pipedrive deals, Gmail threads, and Slack messages — cited synthesis across open and private sources.
Core public federators (SEC EDGAR, arXiv, Internet Archive, ClinicalTrials.gov mirror, OpenAlex live search) are keyless. Optional enrichments (Google Scholar, Patents) use SERP API keys when configured.
Gyri federates into one graph. Agents orient with recall and ground, capture with reflect, and commit with promote — the full epistemic lifecycle via MCP think.
think verb=recallSemantic orient — load prior cited conclusions before you re-derive from scratch.
think verb=groundFTS-only orient on live federated CRM, email, and Slack — zero embed cost.
think verb=considerClassify novelty against the workspace corpus before you commit a thesis.
think verb=reflectCapture drafts, tensions, and questions as typed thoughts on the graph.
think verb=traverseMultihop GraphQL in one think call — deal → contact → email → ticket.
think verb=fetchHydrate full rows by ref when search or traverse surfaced the right node.
think verb=promoteGated commit — draft thought → durable cited insight the whole team recalls.
think verb=wishNatural-language buildout — queue workspace types, connectors, and workflows.
Full catalog via MCP think verb=catalog · Why Gyri think verbs beat API wrappers → · MCP for Claude & Cursor
Cross-links across product, think-verb guides, solutions, and native integrations — every page connects back to the Gyri agentic knowledge base.
Native connectors with cited search, Gyri think verbs, and MCP — browse all 65+