Skip to main content

agentdata

PyPI License Python Commands

Government registries, sanctions lists, procurement portals, and health-agency databases hold the decisive facts about companies — scattered across 60+ public APIs, each with its own pagination, rate limits, and undocumented quirks.

agentdata puts 117 of those datasets behind one interface: a pure-standard-library Python client and CLI across 13 jurisdictions. No API keys, no accounts — politeness and caching are built in, and every upstream gotcha we hit live is already pinned.

Two API families

Family Where it runs Credentials Cost
Enrichment Locally — the SDK calls public government / open-data APIs from your machine none free
Corpus Hosted service operated by dicaria credentials issued by dicaria per service agreement

Most commands are enrichment: they need no configuration, no keys, no account. Corpus commands are marked in the docs and require credentials issued by dicaria under a separate service agreement — contact contact@dicaria.com.

What can you ask it?

Commands follow <domain> <source>_<dataset> — one command per upstream dataset, parameters kept under their upstream names. Every row below works as agentdata <domain> <command> … from the shell, or c.<domain>.<command>(…) from Python.

Question Commands
Is this company sanctioned? legal csl_screening_list · legal co_sic_sanctions · legal wb_debarred_firms · legal ca_sema_sanctions
Who owns or controls it? company gleif_direct_parent · company no_brreg_roller · company fr_recherche_search
Did it win public contracts? procurement br_pncp_contracts · procurement ungm_contract_awards · procurement wb_procnotices
Is its drug or device approved — or recalled? healthcare fda_drug_approvals · healthcare gb_mhra_alerts · healthcare fda_drug_recalls
What does this facility or fleet emit? esg climatetrace_sources · esg thetis_mrv_datasets · esg paris_mou_detentions
Pull a company card from a national registry company ch_zefix_firm · company co_rues_companies · company kr_hometax_biz_status
How big is the country it operates in? economy wb_wdi_values · economy eurostat_table · economy fred_series
Convert an EUR amount, or read a bilateral trade flow economy ecb_fx_rates · economy un_comtrade_trade

Why not just call the APIs yourself?

You can — and then you get to rediscover what is already pinned here:

  • Quirks are pre-solved, not rediscovered. Every command encodes traps we hit against the live API: the UN Global Marketplace search behind an anti-forgery token dance; Socrata endpoints that silently ignore documented parameters; the gov.uk content API that 404s when you append .json; registries that clamp your page size without an error.
  • One envelope across all 117 commands. Query echo, a plain-language reason, evidence rows with a checkable quote and source URL, source metadata, and a jurisdiction chapter — your code parses one shape.
  • Upstream parameter names, verbatim. What the official API docs call a parameter is what the SDK takes — no invented vocabulary to unlearn.
  • Polite by default. Per-source rate limits are enforced before every request (rate-limits ledger); responses are cached locally, and a cache hit costs no rate budget.
  • Zero dependencies. Python 3.10+ standard library only.

Coverage

117 datasets · 80 upstream providers · 13 jurisdictions: global 39 · US 37 · EU 12 · UK 11 · Canada 5 · Colombia 3 · Australia 2 · Switzerland 2 · Norway 2 · Brazil 1 · Finland 1 · France 1 · Korea 1.

Domain Commands Sources
healthcare 31 US FDA approvals & recalls, ClinicalTrials.gov, RxNav, DailyMed, AccessGUDID, UK MHRA alerts, Health Canada DPD & MDALL, EUDAMED, RASFF & Safety Gate (EU), TGA (AU), Europe PMC, MeSH
company 21 GLEIF, SEC EDGAR, FDIC, USAspending, TED, VIES, UK Contracts Finder & FTS, Zefix (CH), Brreg (NO), YTJ (FI), recherche-entreprises (FR), RUES (CO), Hometax (KR), ROR
esg 12 Climate TRACE, EITI, EU ETS (EUTL), THETIS-MRV (EU shipping), EPA FRS, Paris MoU, EU Air Safety List
legal 19 US consolidated screening list, eCFR, Federal Register, LDA filings, CourtListener, DG COMP, UK CMA cases, UK Electoral Commission, TNA case law, SIPRI, SIC sanctions (CO), MDB debarment rosters (WB/AfDB/IDB), Canada SEMA
research 10 OpenAlex, NIH RePORTER, NSF, Crossref, UKRI GtR, iCite, bioRxiv, OpenCitations
procurement 7 PNCP (BR), SECOP II (CO), UNGM, World Bank, New York Authorities / MTA / OGS (US)
security 2 OSV, CISA KEV
economy 15 World Bank WDI, Eurostat, ECB reference rates, FRED, WHO xMart, UN Comtrade, ILOSTAT

Show me a response

Real output of agentdata healthcare rxnav_rxcui_by_name --name atorvastatin — every command returns this shape:

{
  "ok": true,
  "domain": "healthcare",
  "tool": "rxnav_rxcui_by_name",
  "input": {
    "name": "atorvastatin"
  },
  "from_cache": false,
  "reason": "RxNav normalization: drug name 'atorvastatin' → RxCUI 83367 (ingredient level)",
  "result": {
    "rxcui": "83367",
    "normalized_name": "atorvastatin",
    "synonym": null,
    "tty": "IN",
    "suppress": "N"
  },
  "evidence": [
    {
      "quote": "RxCUI 83367 = atorvastatin",
      "url": "https://rxnav.nlm.nih.gov/REST/rxcui/83367/properties.json"
    }
  ],
  "source": {
    "provider": "rxnav",
    "execution": "local",
    "from_cache": false,
    "observed_at": "2026-11-02T03:28:22.213Z"
  },
  "request_id": "3f343e2f-3b08-46e8-ac69-8ee05adce548",
  "query": {
    "source": "raw",
    "upstream": {
      "name": "atorvastatin"
    }
  },
  "jurisdiction": "US"
}

Install

From PyPI:

python -m pip install agentdata

For a reproducible install, pin the release: python -m pip install agentdata==0.3.26.

From a release tarball — no git required:

python -m pip install https://github.com/dicaria/agentdata/archive/refs/tags/v0.3.26.tar.gz

Or via git (pin a tag for reproducible installs):

python -m pip install git+https://github.com/dicaria/agentdata.git@v0.3.26

Or track the latest release (convenience for agents and scripts — a fresh release does not trigger a reinstall under the same URL, so pass --force-reinstall when you want the new one):

python -m pip install --force-reinstall https://github.com/dicaria/agentdata/releases/latest/download/agentdata-latest.tar.gz

Quick start (Python)

from agentdata import Client

c = Client()  # zero config: enrichment commands work immediately

c.healthcare.fda_drug_recalls(search='recalling_firm.exact:"SV Labs Toronto Corporation"')
c.company.gleif_lei_records(lei="5493001KJTIIGC8Y1R12")           # LEI -> entity identity card (GLEIF)
c.company.ch_zefix_firm_search(name="siemens")                    # Swiss commercial registry (Zefix)
c.esg.climatetrace_sources(owner_ids="E100000001492", year=2023)  # owner -> facility-level emissions
c.legal.csl_screening_list(name="VTB BANK")                       # sanctions screening (US CSL)
c.research.openalex_works(search="vaccine", ror="01xdqrp08")
c.procurement.br_pncp_contracts(data_inicial="20260901", data_final="20260930", pagina=1)
c.security.osv_vulns(package="lodash", ecosystem="npm", version="4.17.15")
c.economy.wb_wdi_values(country="CHN", indicator="NY.GDP.MKTP.CD", date="2020:2023")  # World Bank indicator values
c.economy.ecb_fx_rates(currency="USD", start="2026-10-01", end="2026-10-31")  # euro reference rate (1 EUR = X)

Corpus commands use the same shape with hosted credentials:

c2 = Client(base_url="https://…", api_key="mk_live_…")  # PAT issued by dicaria
c2.company.read(id=1476, level="tier2")

Quick start (CLI)

Nine entry points — agentdata plus one command per domain:

agentdata healthcare rxnav_rxcui_by_name --name atorvastatin
agentdata company gleif_lei_records_search --filter-entity-legal-name "Siemens" --page-size 3
agentdata legal csl_screening_list --name "VTB BANK"
agentdata esg climatetrace_sources --owner-ids E100000001492 --year 2023
agentdata procurement br_pncp_contracts --data-inicial 20260901 --data-final 20260930 --pagina 1
agentdata economy wb_wdi_values --country CHN --indicator NY.GDP.MKTP.CD --date 2020:2023

If a domain entry-point command (company, legal, …) collides with another tool on your machine, python -m agentdata <domain> … is the equivalent invocation.

Caching

Every response is cached in a per-user SQLite cache shared across virtual environments and processes — cache hits cost no rate budget (see docs/domains/rate-limits.md). A fresh install in a new virtual environment will therefore hit entries written by earlier runs on the same machine; that is by design.

Default location %LOCALAPPDATA%\agentdata\cache.db on Windows; ~/.cache/agentdata/cache.db on macOS/Linux
Override AGENTDATA_CACHE_DIR environment variable (CLI: --cache-dir)
Bypass --no-cache (CLI) / no_cache=True (Python)
Clear delete the file — every entry re-fetches on demand

Entry lifetimes follow the per-source TTL table in the rate-limits ledger; immutable lookups (e.g. drug name → RxCUI) are cached permanently.

Documentation

License and terms

  • The code in this repository is licensed under the license in LICENSE.
  • The data returned by the SDK is governed by the terms of each upstream source; the SDK grants no data rights. See TERMS.md.

Contact

Metadata

Release files for agentdata 0.3.26

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agentdata 0.3.26
File Size Uploaded Provenance Actions
agentdata-0.3.26.tar.gz 300.8 kB With provenance Details for agentdata-0.3.26.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agentdata 0.3.26
File Interpreter ABI Platform Actions
agentdata-0.3.26-py3-none-any.whl Python 3 none any Details for agentdata-0.3.26-py3-none-any.whl

Total release size: 673.3 kB

Release files / agentdata-0.3.26.tar.gz

Download URL agentdata-0.3.26.tar.gz
Size 300.8 kB
Tags Source
SHA-256 checksum
How to use checksums
2a91dfa0d1e9f76d0e3d4f22e3123065f4c2915ac80faf63e5071d808bcfdd30
BLAKE2b-256 checksum
How to use checksums
10ab3721ee4b7b53b99fbdd12fc79866a63990487a20d919c4ddef1ac20cea60
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 3, 2026.

Transparency log

Release files / agentdata-0.3.26-py3-none-any.whl

Download URL agentdata-0.3.26-py3-none-any.whl
Size 372.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
efce10a81cfdce3b7d8b6b82e9c3fd72d183a6c93c3f74cc594bc68d6748c290
BLAKE2b-256 checksum
How to use checksums
7b05041d46289f059d832250d1736b1940333ea703f5a143304946a47cb24e31
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 3, 2026.

Transparency log

Security for agentdata 0.3.26

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for agentdata-0.3.26.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 3, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page