DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to cross-check corpus facts against openFDA and ClinicalTrials.gov with On Co

Run the fact-check and audit scripts to flag stale or contradictory oncology records.

  • Research
  • Intermediate
  • 45 minutes
  • From the README
  • Any agent

Who it is forA maintainer or researcher who wants to find outdated approvals or trial statuses in the corpus before relying on them.

The problemApproval and trial facts change over time, and a static record can quietly fall behind the registries it cites.

The outcomeA list of records that disagree with openFDA or ClinicalTrials.gov, or that the audit marks as stale or contradictory.

What you need first

  • Node.js and npm (inferred, needed for the repository scripts)
  • Git and a GitHub account for cloning the repository or opening issues and pull requests
  • An MCP-capable client or agent for the MCP server (optional)

Steps

  1. Clone the repository and run npm install in its folder. (inferred, check the README)
  2. Run npm run validate to confirm the corpus parses before checking it.
  3. Run npm run factcheck to cross-check against openFDA and ClinicalTrials.gov.
  4. Run npm run audit to find stale or contradictory facts.
  5. Open each flagged record, check the primary source and open an issue or pull request if the record is wrong.

Prompt for your agent

In a local clone of judegomila/OnCo, run `npm run validate`, then `npm run factcheck` and `npm run audit`. Expected output is a list of flagged record ids with the field, the stored value and the source value. Verify each flag against the linked primary source before reporting it as an error.

Caveat. The README warns that facts may be wrong, so a flag from the checks is a prompt to verify at source, not proof that a record is incorrect.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page