My coding agent read 92,348 tokens to learn what NumPy is. So I built leantext.

Description and use

<p>I asked my coding agent a simple question about a Python package. It fetched the package's PyPI page and read <strong>92,348 tokens</strong>.</p> <p>The part of that page I actually cared about, the project description, is about <strong>2,000 tokens</strong>. The rest? Navigation, a sidebar, a footer, and a hidden "Download files" tab listing every file of every NumPy release with its security hash. You never see that list in a browser. My agent read all of it anyway, and I paid for it.</p> <p>That's the problem I built <strong>leantext</strong> to solve.</p> <h2> What leantext does </h2> <

Problem

<p>I asked my coding agent a simple question about a Python package. It fetched the package's PyPI page and read <strong>92,348 tokens</strong>.</p> <p>The part of that page I actually cared about, the project description, is about <strong>2,000 tokens</strong>. The rest? Navigation, a sidebar, a footer, and a hidden "Download files" tab listing every file of every NumPy release with its security hash. You never see that list in a browser. My agent read all of it anyway, and I paid for it.</p> <p>That's the problem I built <strong>leantext</strong> to solve.</p> <h2> What leantext does </h2> <

Outcome

<p>I asked my coding agent a simple question about a Python package. It fetched the package's PyPI page and read <strong>92,348 tokens</strong>.</p> <p>The part of that page I actually cared about, the project description, is about <strong>2,000 tokens</strong>. The rest? Navigation, a sidebar, a footer, and a hidden "Download files" tab listing every file of every NumPy release with its security hash. You never see that list in a browser. My agent read all of it anyway, and I paid for it.</p> <p>That's the problem I built <strong>leantext</strong> to solve.</p> <h2> What leantext does </h2> <

Evidence

My coding agent read 92,348 tokens to learn what NumPy is. So I built leantext.

Source