Ready-to-use agents.
Each one does the whole job, start to finish: hand it a few web pages and get back the thing you actually wanted. Lyrenth is the part that reads, and it hands your model the article itself, with the menus, banners, scripts and markup already gone. Free, open, and they run on your machine.
Pick the job, not the tool.
Every agent here reads the pages you hand it and writes the answer you asked for, with a number beside each claim pointing at the page it came from. Open one to see what it takes and what it gives back.
Product comparison
Put two product pages side by side and get a table of what is actually different.
See what it does →Company brief
Read a company's own pages and get a plain summary of what they do and who they sell to.
See what it does →Documentation answers
Point it at documentation pages and get the answer with the exact page and section it came from.
See what it does →Research brief
Give it the pages to read and get an answer that shows where every part came from.
See what it does →Article summary
Hand over a long article and get the argument in a few hundred words: what it claims, what it rests on, and what it leaves out.
See what it does →Table from pages
Give it several similar pages and get one table, a row per page, with an empty cell wherever a page did not say.
See what it does →Terms in plain English
Get terms of service or a privacy policy in plain English, with the clause behind every point.
See what it does →Who works there
Read a company's own team and careers pages and get who works there and what they are hiring for.
See what it does →What it works with
Get the list of tools a product says it works with, grouped, with the page each claim came from.
See what it does →News digest
Give it the last few days of articles and get one briefing: what happened, what is new, and which source said what.
See what it does →One job, four runs.
This is a morning of homework before a meeting with a company. Each run reads its own pages and stands on its own, so you can stop after any of them. The last one hands you a file.
Start with what they say they do
Their about page, their manifesto and their careers page.
Find out who you are talking to
The leadership page and the list of open roles.
Put their product next to the one you use
An encyclopedia article for each product.
Leave with a file, not fifteen tabs
Their three product pages, and one sentence asking for CSV.
| A | B | C | D | E | F | G | H | |
|---|---|---|---|---|---|---|---|---|
| 1 | Product Name | Type | Supported Platforms | Privacy & Tracking | Price | Open Source | AI Policy | Source |
| 2 | Firefox | fast, private browser | Windows 8.1 and below, macOS 10.14 and below, App Store, Google Play, desktop, mobile, tablet | Blocks trackers automatically, don’t sell your personal data | AI features are optional by design | [1] | ||
| 3 | Thunderbird | app | Android, Windows, Mac, Linux | don’t collect personal data, sell ads in your inbox | Free forever | open source | don’t secretly train AI with your private conversations | [2] |
| 4 | Mozilla VPN | virtual private network | Windows | No logging, tracking or sharing of network data | €4.99/month, €9.99/month | open source | [3] |
Saved as products.csv, this is the file your spreadsheet opens. Every cell is the wording the product page used, and the blanks are the questions those pages did not answer.
One command, one key.
Nothing to install, nothing to wire together. The agents all come from one package, lyrenth-agents, and every line of it is public.
Run it in place
One line in your terminal with the pages you care about. Each agent page shows its own command, already filled in with real URLs you can paste as they are.
Bring your own assistant
With just your Lyrenth key, an agent reads the pages and prints the finished prompt with its numbered sources, ready to paste into whichever assistant you already use. Point it at any OpenAI-compatible endpoint instead and it answers on its own.
Nothing fails quietly
A page that could not be read is listed with the reason, so you always know what the answer was built from. An answer never comes back pretending it read a page it did not.