Keep added an in-app feed reader so saved links can be read directly inside its bookmark store for agent workflows. Use it to turn bookmarks, RSS feeds, and markdown exports into reusable context instead of scattered tabs.
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.
Cursor shipped Instant Grep, a local regex index built from n-grams, inverted indexes, and Bloom filters that drops large-repo searches from seconds to milliseconds. Faster candidate retrieval shortens the coding-agent loop, especially when ripgrep-style scans become the bottleneck.
releaseOpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.
releaseCursor shipped Instant Grep, a local regex index built from n-grams, inverted indexes, and Bloom filters that drops large-repo searches from seconds to milliseconds. Faster candidate retrieval shortens the coding-agent loop, especially when ripgrep-style scans become the bottleneck.
breakingChatGPT now saves uploaded and generated files into an account-level Library that can be reused across conversations from the web sidebar or recent-files picker. It removes repetitive re-uploading and makes past PDFs, spreadsheets, and images part of a persistent working context.
breakingEpoch AI says GPT-5.4 Pro elicited a publishable solution to one 2019 conjecture in its FrontierMath Open Problems set, with a formal writeup planned. Treat it as an early milestone worth reproducing, not blanket evidence that frontier models can already automate math research.
Anybody know anybody at Google to help @suganthan get his handle back?
Hi @TeamYouTube. I temporarily released my handle @suganthan to transfer it between my own accounts. The exact second it was released, an automated sniper bot registered a new account and stole it. The bot account was created today with zero content. Please help me recover it.
In the latest version of Keep I added a simple feed reader to, well, read your saved bookmarks Originally built this for myself purely for my agents but I had a few requests for this so you have to give the people what they want* keep.md *sometimes ;)
