Problem or use case
Sometimes getting a whole website (or worse yet an IA archive of a website) is hard, and Thoth could have a tool to reduce friction, ideally webpage fetching + hyperlink-awareness + exclusion of index/pagination + aware of keywords/tagging/categories, can be streamlined a little
Proposed solution
Based on the following toolkit https://github.com/aaronjmars/soul.md
See also Ribbonfarm as an example aaronjmars/soul.md#20
Area
Memory / knowledge graph
Alternatives considered
No response
Problem or use case
Sometimes getting a whole website (or worse yet an IA archive of a website) is hard, and Thoth could have a tool to reduce friction, ideally webpage fetching + hyperlink-awareness + exclusion of index/pagination + aware of keywords/tagging/categories, can be streamlined a little
Proposed solution
Based on the following toolkit https://github.com/aaronjmars/soul.md
See also Ribbonfarm as an example aaronjmars/soul.md#20
Area
Memory / knowledge graph
Alternatives considered
No response