Keep adds an in-app feed reader for saved bookmarks

• Keep added a "simple feed reader" so users can read saved bookmarks inside the product instead of bouncing back out to the original tab, according to the launch post.
• The feature was built "purely for my agents" before being opened up more broadly, which frames it as an agent-context tool as much as a human reading UI, per the thread context.
• Keep’s product page already exposes a REST API, CLI, RSS ingestion, and markdown-based storage, so the new reader lands inside an existing stack for saving, searching, and reusing web content.
• A supporting screenshot from a follow-up post also points to broader ingestion work this week, including Atom, JSON Feed, h-feed, feed autodiscovery, and a unified markdown format.

Keep’s latest update adds an in-app reader for saved links. In the launch post, Ian Nuttall describes it as a "simple feed reader" to "read your saved bookmarks," and the attached screen demo shows a saved-item list opening directly into article text inside Keep.

That matters because Keep is not just a read-later app. Its product page positions the service as a bookmark store that turns saved pages into searchable markdown, with API and CLI access for downstream use. The new reader closes a gap in that workflow: the same cleaned content used for retrieval and agent context is now readable inside the app rather than only exported or searched.

The clearest implementation detail is the origin story. Nuttall says the reader was "built this for myself purely for my agents" in the original thread, which suggests the feature came from a workflow where bookmarks are first collected as machine-usable context and only then surfaced for humans.

A follow-up screenshot in the feature list shows the reader arriving alongside plumbing changes that make that context more uniform: Keep now supports Atom, JSON Feed, and h-feed; can discover feeds automatically from a URL; and unifies saved content into "the exact same" markdown structure with metadata frontmatter. The same post also mentions better article formatting, improved YouTube transcript extraction, CSV and Safari bookmark imports, and tags plus auto-tagging, which all point in the same direction: less brittle ingestion and cleaner stored context for both humans and agents.