I build apps and the agent tooling that builds them.
620
Parses RSS and Atom feeds, extracting data like titles, descriptions, links, and various multimedia attributes. Supports custom configurations for networking and character sets, and integrates with Java projects using CompletableFuture.
5
Extracts main article content and metadata from static HTML, strips navigation, ads, and clutter, returns clean Markdown and/or cleaned HTML, supports domain-scoped extractors and debug output.