piloterr

piloterr

Fetch web pages for the built-in web_extract tool through the Piloterr web scraping API, with optional JavaScript rendering or anti-bot unblocking. Extract only; pair it with a search backend for web_search. Disclosure — sends each URL to api.piloterr.com with your PILOTERR_API_KEY, and calls can use Piloterr credits. Reads the key only through Hermes's secret scope. Registers no tools, no hooks or middleware, writes no files, starts no processes, has no telemetry or self-updater, and uses only the Python standard library.

piloterrWebv1.0.0Updated 22 minutes ago

About

Piloterr for Hermes Agent

Fetch web pages for the built-in web_extract tool through the Piloterr web scraping API, with optional JavaScript rendering or anti-bot unblocking.

Install

hermes plugins install piloterr

Hermes asks for PILOTERR_API_KEY during the install. Create a key in the Piloterr dashboard.

Then select it in hermes tools, or in ~/.hermes/config.yaml:

web:
  extract_backend: piloterr

It is extract only, so keep a search backend for web_search.

Settings

| Setting | Default | Meaning |
|---|---|---|
| engine | crawler | crawler (plain HTTP, cheapest), rendering (headless browser for JavaScript pages) or webunlocker (gets past anti-bot protection, most expensive). |

What it does on your machine

Network: calls https://api.piloterr.com only, with your PILOTERR_API_KEY. Calls can use credits on your Piloterr account (pricing).
Credentials: reads the key only through Hermes's secret scope. It stores nothing.
Nothing else: no files written, no processes started, no telemetry, no self-update. Standard library only, no dependencies.

Development

python -m pytest

The tests mock the network and run without Hermes installed.

Contact

Source: https://github.com/piloterr/hermes-plugin-piloterr
Piloterr: https://www.piloterr.com
Issues: https://github.com/piloterr/hermes-plugin-piloterr/issues

License

MIT

README from the reviewed commit 04551c3; it updates when the author re-pins.