Who it is forA product manager or analyst who needs to compare free tiers or plans across several vendors and wants the reading done in their own open browser tabs.
The problemComparing plans means opening each vendor site, finding the right page, and copying limits into a spreadsheet by hand.
The outcomeA comparison table with the sources used and a short takeaway on the trade-offs, produced from pages you already had open.
What you need first
- Node 24 or newer, checked with `node -v`
- Chrome 114 or newer
- The claude CLI, the cursor-agent CLI, or both, already logged in to a subscription (Claude Pro is enough)
- Git, to clone the repository
Steps
- Run
git clone https://github.com/Endokelp/Endoplexity.gitand thencd Endoplexity. - Run
npm install, thennpm startto run the bridge in the foreground (ornpm run setupon Windows for autostart). - Open
chrome://extensions, turn on Developer mode, click Load unpacked, and select theextension/folder. - Open the first pricing page in Chrome, then click the Endoplexity icon to open the side panel.
- Type the instruction naming each vendor, type
@to hand over other open tabs, and press Run.
Prompt for your agent
Using the Endoplexity repo at <repo path>, run a task in the Chrome side panel that reads the pricing pages at <vendor URLs> and returns a comparison table of free-tier limits with the source URL for each row. Verify that every row names the page it came from and that no figure is missing its source.
Caveat. Autostart via `npm run setup` is Windows-only for now, so macOS and Linux users need to keep `npm start` running in a terminal.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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