Reading
8 products ranked by how much of their useful core an AI coding agent can realistically reproduce.
NewsBlur
The core loop is small enough for a capable coding agent to produce a useful local version. For NewsBlur, self-host a feed reader with training filters, folders, and full-text search. The hard boundary is hosted convenience, native apps, story intelligence, and community features, plus capture polish, sync, and content partnerships.
Pinboard
The core loop is small enough for a capable coding agent to produce a useful local version. For Pinboard, run a fast private bookmark archive with tags, notes, and full-text search. The hard boundary is hosted longevity, simple api, archive service, and zero-maintenance reliability, plus capture polish, sync, and content partnerships.
Reeder
The core loop is small enough for a capable coding agent to produce a useful local version. For Reeder, build a native feed and read-later client with local search and sync through a chosen account. The hard boundary is native apple polish, broad account support, gestures, and long-term maintenance, plus capture polish, sync, and content partnerships.
GoodLinks
The core loop is small enough for a capable coding agent to produce a useful local version. For GoodLinks, save readable pages locally across Apple devices with tags and highlights. The hard boundary is native apple polish, icloud sync, shortcuts, and mobile capture, plus capture polish, sync, and content partnerships.
Instapaper Premium
The core loop is small enough for a capable coding agent to produce a useful local version. For Instapaper Premium, save readable versions of permitted pages, highlight them, and search the archive. The hard boundary is mobile capture, sync, text-to-speech, kindle integration, and parser maintenance, plus capture polish, sync, and content partnerships.
Recall
The core loop is buildable, but a dependable replacement becomes a substantially larger project. For Recall, save user-provided sources, summarize them, and build a linked personal knowledge graph. The hard boundary is hosted extraction, model routing, browser capture, sync, and knowledge-graph polish, plus capture polish, sync, and content partnerships.
Matter
The core loop is buildable, but a dependable replacement becomes a substantially larger project. For Matter, save articles and newsletters into a clean reading queue with highlights and notes. The hard boundary is email ingestion, mobile apps, text-to-speech, sync, and polished capture, plus capture polish, sync, and content partnerships.
Readwise
The core loop is buildable, but a dependable replacement becomes a substantially larger project. For Readwise, import highlights from user-exported files, review them with spaced repetition, and export notes. The hard boundary is broad source integrations, sync, daily review polish, and knowledge-tool exports, plus capture polish, sync, and content partnerships.