What you can do with Qanat

3 use cases

• Screen companies as they stood on a past date

  Run a metric threshold screen on SEC filings using only what was public on a chosen date.

  • Qanat
  • Money
  • Intermediate
  View prompt

  In the Qanat project at <project-folder>, run a screen for metric pe below 30 as of <date> using the qanat screen command. Return the companies that passed, the count evaluated, and the count that could not be evaluated. Verify that the list is shown together with the unevaluated count so no companies are silently dropped.

  Share Save

• Measure what screened companies did between filings

  Run a screen over a date window and read each passing company's return between its own filing dates.

  • Qanat
  • Money
  • Intermediate
  View prompt

  Using the Qanat project at <project-folder>, run a windowed screen from <start-date> to <end-date> on the metric and threshold <rule>. Report the per-company return from each company's own filing to its next filing, along with the evaluated and unevaluated counts. Verify that no average or aggregate has been added, since Qanat reports per-company returns only.

  Share Save

• Ask an AI agent questions over dated filings

  Connect an MCP client to Qanat's read-only research scope and query SEC filings and screens in plain language.

  • Qanat
  • Money
  • Intermediate
  View prompt

  Using the qanat MCP server in <project-folder> with research scope, answer this question: <question>. Reply with the answer, the source filings or tables used, and the dates they were public. Verify that every number comes from a Qanat tool call and not from memory.

  Share Save

How to use Qanat

1. Check you have what it needs: Python 3.10 or newer; uv or pip to install qanat-fdtl; A contact email for the SEC_USER_AGENT setting, which the SEC uses to identify requests (no API key or account).
2. Open fidetolabs/qanat on GitHub and read the README and license.
3. Install Qanat with uv tool install qanat-fdtl (or pip install qanat-fdtl).
4. Set your contact address with export SEC_USER_AGENT="your name [email protected]".
5. Create a demo project with qanat init my-research --demo && cd my-research.
6. Validate the project file with qanat check.

These steps come from our top use case, Screen companies as they stood on a past date, which also has a copy-paste agent prompt.

Qanat alternatives · Best AI repos for Money

About this repo

• Who it is forInvestment researchers and quant-minded analysts who want stock screens free of look-ahead bias, and the AI agents they work with.
• Why it is hot
• LanguagePython
• Sourcegithub.com/fidetolabs/qanat · Back to Hot repos

Requirements

• Python 3.10 or newer
• uv or pip to install qanat-fdtl
• A contact email for the SEC_USER_AGENT setting, which the SEC uses to identify requests (no API key or account)
• An MCP-capable agent client, only for the agent use case

Related repos

• Trended earlier Finathink Finathink is a local-first Python workbench that turns user data, evidence, factors, backtests, risk checks and paper portfolios into a traceable research record with offline HTML reports.
• Trended earlier Northcinder NorthCinder is an open-source MCP server that compares products from stores you choose, explains its ranking, and asks for your approval before any purchase.
• Trended earlier DSH Cost Meter dsh-cost-meter is a cost tracking plugin for the DeepSeek Harness web GUI that shows session and model costs, token usage, budgets, provider balances, and coding-plan quotas.