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

How to pull matching lines from a long or endless web page with Axuse

An agent scrolls a feed until a term appears, then returns only the matching lines.

Authorization notice. Axuse is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA researcher or analyst who needs to find mentions of a term in a long feed, infinite list, or many pages.

The problemLoading a long page into an agent's context uses many tokens, and infinite lists require manual scrolling.

The outcomeThe agent returns only the lines that match the term, with the page text it found, instead of the whole page.

What you need first

  • Node.js 22 or newer
  • A Chromium-family browser (Chrome, Edge, Chromium, or Chrome for Testing), or AXUSE_BROWSER set to its path
  • git to clone the repository
  • Codex or Claude Code installed as the MCP host

Steps

  1. git clone https://github.com/ctoldigital/axuse.git
  2. cd axuse
  3. node src/cli.js doctor
  4. codex mcp add axuse -- node /abs/path/axuse/src/cli.js mcp
  5. Ask the agent to scroll until the term appears, then observe only the matching lines.

Prompt for your agent

Using the axuse MCP server, open <page URL>, scroll until the text <search term> appears, then observe only the lines matching that text. Return the matching lines as a list, and check that each line appears in the page when you observe it again.

Caveat. The README describes ax_open_many as a bounded list, so very large batches must be split into several runs.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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