LYRENTH
AgentsDocsPricingBenchmarksIndex statsAboutBlogFor site ownersStatusContact
Agents

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.

Read the source on GitHub →MIT, and lyrenth-agents on PyPI
compare · lyrenth-agents
$uvx lyrenth-agents compare https://en.wikipedia.org/wiki/PostgreSQL https://en.wikipedia.org/wiki/MySQL
recipe compare: Product comparisonread[1] PostgreSQL - Wikipedia 30,000 tokens https://en.wikipedia.org/wiki/PostgreSQLread[2] MySQL - Wikipedia 30,000 tokens https://en.wikipedia.org/wiki/MySQLcontext 60,000 tokens from 2 sources (raw HTML would be 412,333)
| Feature | PostgreSQL | MySQL |
| :--- | :--- | :--- |
| Software Type | Free and open-source object relational database management system [1] | free and open-source relational database management system (RDBMS) [2] |
| License | PostgreSQL License (free and open-source, permissive) [1] | GPLv2 or proprietary [2] |
| Developer | PostgreSQL Global Development Group [1] | Oracle Corporation [2] |
| Initial Release | 8 July 1996; 30 years ago (1996-07-08) [1] | 23 May 1995; 31 years ago (1995-05-23) [2] |
| Stable Release | 18.6 / 13 August 2026 [1] | 26.7.0 / 28 July 2026 [2] |
| Written In | C (and C++ for the LLVM dependency) [1] | C, C++ [2] |
| Supported Operating Systems | Windows, Linux, macOS, FreeBSD, and OpenBSD [1] | Linux, Solaris, macOS, Windows, FreeBSD [2] |
| Concurrency Architecture | process-based (not threaded), and uses one operating system process per database session [1] | multi-threaded [2] |
| Default Storage Engine | not stated on the pages given [1] | InnoDB [2] |
| SQL Standards Compliance | conforms to at least 170 of the 177 mandatory features for SQL:2023 Core conformance [1] | A broad subset of ANSI SQL 99, as well as extensions [2] |
| Primary Command-Line Tool | psql [1] | mysql client [2] |
| Primary GUI Administration Tool | pgAdmin [1] | MySQL Workbench [2] |

### Clearest Differences

- PostgreSQL is an object relational database management system [1], whereas MySQL is a relational database management system [2].
- PostgreSQL is released under the PostgreSQL License [1], while MySQL is released under GPLv2 or proprietary licenses [2].
- PostgreSQL is developed by the PostgreSQL Global Development Group [1], whereas MySQL is developed by Oracle Corporation [2].
- PostgreSQL was initially released on 8 July 1996 [1], whereas MySQL was initially released on 23 May 1995 [2].
- PostgreSQL server is process-based (not threaded) [1], whereas MySQL is a multi-threaded server [2].
- MySQL uses InnoDB as its default storage engine [2], while a default storage engine is not stated on the pages given for PostgreSQL [1].
- PostgreSQL conforms to at least 170 of the 177 mandatory features for SQL:2023 Core conformance [1], whereas MySQL supports a broad subset of ANSI SQL 99 [2].

Sources
  [1] PostgreSQL - Wikipedia  https://en.wikipedia.org/wiki/PostgreSQL
  [2] MySQL - Wikipedia  https://en.wikipedia.org/wiki/MySQL
A real run, captured 2026-09-21 and printed here as it came back.
Together

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.

Company briefWhat they do, for whom
Who works thereNames, roles and open jobs
Product comparisonOne table of real differences
Table from pagesOne row for every product
products.csvOpens in your spreadsheet
01

Start with what they say they do

Their about page, their manifesto and their careers page.

uvx lyrenth-agents brief https://www.mozilla.org/en-US/about/ https://www.mozilla.org/en-US/about/manifesto/ https://www.mozilla.org/en-US/careers/
→What they do, who they sell to, how they describe themselves, and a list of what their own pages never answer. 3 pages, 6,664 tokens of text. See this agent →
02

Find out who you are talking to

The leadership page and the list of open roles.

uvx lyrenth-agents people https://www.mozilla.org/en-US/about/leadership/ https://www.mozilla.org/en-US/careers/listings/
→Names and roles as the pages state them, and every opening they list, which is where a company says what it is really building. 2 pages, 5,583 tokens of text. See this agent →
03

Put their product next to the one you use

An encyclopedia article for each product.

uvx lyrenth-agents compare https://en.wikipedia.org/wiki/Firefox https://en.wikipedia.org/wiki/Google_Chrome
→One table of what is actually different, with the page number in every cell and a blank wherever a page stayed silent. 2 pages, 60,000 tokens of text. See this agent →
04

Leave with a file, not fifteen tabs

Their three product pages, and one sentence asking for CSV.

uvx lyrenth-agents extract -q "Write the table as CSV with a header row, one row per product, and nothing before or after the CSV." https://www.mozilla.org/en-US/firefox/new/ https://www.thunderbird.net/en-US/ https://www.mozilla.org/en-US/products/vpn/
→A sheet of their products, one row each, that you save as a .csv and open in a spreadsheet. 3 pages, 5,539 tokens of text. See this agent →
What the fourth run wrote
ABCDEFGH
1Product NameTypeSupported PlatformsPrivacy & TrackingPriceOpen SourceAI PolicySource
2Firefoxfast, private browserWindows 8.1 and below, macOS 10.14 and below, App Store, Google Play, desktop, mobile, tabletBlocks trackers automatically, don’t sell your personal dataAI features are optional by design[1]
3ThunderbirdappAndroid, Windows, Mac, Linuxdon’t collect personal data, sell ads in your inboxFree foreveropen sourcedon’t secretly train AI with your private conversations[2]
4Mozilla VPNvirtual private networkWindowsNo logging, tracking or sharing of network data€4.99/month, €9.99/monthopen 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.

The library

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.

Compare

Product comparison

Put two product pages side by side and get a table of what is actually different.

See what it does →
Company

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 →
Docs

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

Research brief

Give it the pages to read and get an answer that shows where every part came from.

See what it does →
Content

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 →
Data

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 →
Content

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 →
Company

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 →
Data

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 →
Content

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 →
Company

Company pack

Read a company's own pages and leave with a one-page pack for the meeting.

See what it does →
How they run

One command, one key.

No project to set up, nothing to wire together. The agents all come from one package, lyrenth-agents, and every line of it is public. It runs with uv (brew install uv on a Mac), or with pipx run in place of uvx.

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.