Page2AI — Webpage to Markdown di igorsaevets
Turn the page you are reading into clean Markdown for an LLM. Runs in your browser; nothing is sent to the author or any third party. Keeps code blocks with language labels, tables and headings. Uses a site's own Markdown when it publishes one.
Disponibile in Firefox per AndroidDisponibile in Firefox per Android
Scansiona il codice QR per aprire questa estensione in Firefox per Android
Metadati estensione
Informazioni sull’estensione
Page2AI converts the page in your active tab into Markdown that an LLM can actually read, and puts it on your clipboard. One click, or Alt+Shift+M.
What it is for. Pasting a rendered documentation page into a chat gives the model navigation, cookie banners and broken code fences. Page2AI gives it the article: headings, tables, lists, and code blocks with their language labels intact.
What it does with your data. Nothing leaves your machine for the author or any third party. There is no server, no account, no analytics, no telemetry, no crash reporting and no third-party SDK. The extension asks for four permissions and no host permissions at all: activeTab, scripting, clipboardWrite, storage.
The one request it makes. Many documentation sites publish a machine-readable Markdown copy of each page. When you invoke the extension it looks for one on the site you are already reading, and only that site: /llms.txt, /docs/llms.txt, /llms-full.txt, and the page's own .md file if the index names one. Using the site's own Markdown beats converting rendered HTML. Those are same-origin requests made from the page itself. Set "Official Markdown" to never in the popup to switch it off.
Open source. MIT licensed. Source: https://github.com/igorsaevets/page2ai-extension
Measured, not asserted. Extraction quality is benchmarked against trafilatura, Mozilla Readability, Defuddle and Microsoft MarkItDown on a committed corpus of documentation pages, with the protocol registered before the run: https://github.com/igorsaevets/page2ai-benchmark
What it is for. Pasting a rendered documentation page into a chat gives the model navigation, cookie banners and broken code fences. Page2AI gives it the article: headings, tables, lists, and code blocks with their language labels intact.
What it does with your data. Nothing leaves your machine for the author or any third party. There is no server, no account, no analytics, no telemetry, no crash reporting and no third-party SDK. The extension asks for four permissions and no host permissions at all: activeTab, scripting, clipboardWrite, storage.
The one request it makes. Many documentation sites publish a machine-readable Markdown copy of each page. When you invoke the extension it looks for one on the site you are already reading, and only that site: /llms.txt, /docs/llms.txt, /llms-full.txt, and the page's own .md file if the index names one. Using the site's own Markdown beats converting rendered HTML. Those are same-origin requests made from the page itself. Set "Official Markdown" to never in the popup to switch it off.
Open source. MIT licensed. Source: https://github.com/igorsaevets/page2ai-extension
Measured, not asserted. Extraction quality is benchmarked against trafilatura, Mozilla Readability, Defuddle and Microsoft MarkItDown on a committed corpus of documentation pages, with the protocol registered before the run: https://github.com/igorsaevets/page2ai-benchmark
Voto 0 da 0 revisori
Permessi e dati
Permessi obbligatori:
- Salvare dati negli appunti
Raccolta dati:
- Lo sviluppatore dichiara che questa estensione non richiede la raccolta di dati.
Ulteriori informazioni
- Link componente aggiuntivo
- Versione
- 1.3.0
- Dimensione
- 46,12 kB
- Ultimo aggiornamento
- 5 giorni fa (28 lug 2026)
- Categorie correlate
- Licenza
- Licenza MIT
- Informativa sulla privacy
- Consulta l’informativa sulla privacy per questo componente aggiuntivo
- Cronologia versioni
- Aggiungi alla raccolta