EXTENSIONS
Built by operatives — models, drivers, vaults, and reports, the parts that plug into Swamp.
Filter by what you need and pull what fits.
News Scraper
Configurable News Scraper — collects articles from any set of RSS/Atom feeds the user provides. Supports multiple sources with category tagging, deduplication, and date sorting. Includes a multi-language summary report (English, Portuguese, Spanish).
News Reader
Fetches RSS/Atom feeds, learns user preferences, and generates a static HTML news summary page ranked by predicted interest.
News Workflow
Full news feedback loop — gathers feedback from a queue server, fetches feeds from the catalog, deduplicates articles by URL, generates an HTML summary ranked by user preferences, discovers new RSS feeds from article URLs, upserts them into the catalog, and renders a feeds.html catalog listing.
News W Anchor
Posts one unseen article a day from a rotation of satire news feeds (The Onion, ClickHole, Reductress, The Beaverton, The Hard Times, The Daily Mash, NewsThump) to a Discord channel, keeping a ledger so the same joke never lands twice.
Research Collector
Research data collector — gathers intelligence from Hacker News, Lobste.rs,
Discourse
Query Discourse forums via the public REST API. List categories, browse
Feed Catalog
Manages a curated list of RSS/Atom feeds for the news reader.
Feed Discovery
Discovers new RSS/Atom feeds by crawling domains from the news-reader's article URLs and upserting them into the feed-catalog.
Feed Analysis
Analyzes pages gathered by the news-reader, discovers RSS/Atom feeds in each page, and writes a page-discovery-result resource for catalog upsert.
Web Crawl
Automated web reading pipeline — harvests articles from configurable sources (Hacker News, Lobsters, RSS/Atom feeds), evaluates them with an AI agent, learns user interest over time via feedback, and produces a curated HTML report with ranked recommendations. Designed for agent-driven reading workflows where an AI reads on the user's behalf and surfaces what matters.