[agencies]

Depends on required features like cross browser support, cross device support, handling pdfs, ocr images, etc. Some of the mentioned features already exist in the browser. Not sure if the browser vendors are incentivized to develop and maintain such features.

[metadat]

I recall a project showcased on HN that does browser history full text indexing via a proxy. Perhaps that would be a better approach.

[agencies]

Yeah several threads on HN that have lists of tools and pros/cons.