<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
<channel>
  <title>Klyr — What's new</title>
  <link>https://getklyr.ai/whats-new</link>
  <description>What Klyr can do now that it couldn't before, in plain language.</description>
  <language>en</language>
  <item>
    <title>Your clone has its own address, without you having to invent one</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-09-03-your-clone-has-an-address</guid>
    <pubDate>Thu, 03 Sep 2026 09:00:00 GMT</pubDate>
    <description>Connecting two clones used to start with a chore: before anyone could add you, you had to pick a name for yourself and hope nobody had taken it. Now your clone is given its own address the moment it exists, so you are reachable straight away, and nobody loses a good name to whoever asked first. Addresses handed out from here on are long and random, so no one can guess their way to a member who never gave theirs out.

The name people actually read is still yours. Set your display name to whatever you like, change it as often as you like, and your contacts see that — the address underneath simply does the routing. If you already picked an address, you keep it exactly as it is; nothing you chose was renamed.

Try: `/klyr:contacts` and look at the top line — that is your clone's address and the name your contacts see beside it.</description>
  </item>
  <item>
    <title>The install page now tells the truth about your machine</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-08-06-install-that-matches-your-machine</guid>
    <pubDate>Thu, 06 Aug 2026 09:00:00 GMT</pubDate>
    <description>Three things the get-started page was getting wrong, depending on what you run.

On Linux, the command it gave you could stop on its first line without installing anything — it handed a Bash script to a shell that does not speak Bash. It now names Bash, and installs.

On Windows, it offered self-hosted memory as a free choice. On plain Windows that choice cannot work: the memory engine needs Linux containers, so self-hosting there requires WSL2 and Docker Desktop. The page says so now, where you make the choice, instead of after.

And if you moved yourself to beta or canary, re-running the plain install command quietly moved you back to stable. The channels page now carries a command that keeps you on your own track.

Try: if an install ever stopped on you, run the command on /docs/getting-started again — and if you are on beta or canary, take yours from /docs/channels instead.</description>
  </item>
  <item>
    <title>Know whether a memory is a draft or something you've confirmed</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-27-memory-status</guid>
    <pubDate>Mon, 27 Jul 2026 09:00:00 GMT</pubDate>
    <description>When your clone recalls a note, it now tells you whether it's still a draft or something you've approved — so an unverified thought never travels as settled fact. Your clone leans on what you've confirmed and flags the rest, keeping your memory honest by default.

Try: ask your clone about something recent and notice it marks unconfirmed notes as drafts.</description>
  </item>
  <item>
    <title>Choose how early you get new features</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-27-release-channels</guid>
    <pubDate>Mon, 27 Jul 2026 09:00:00 GMT</pubDate>
    <description>Pick the release track that fits you: stable (vetted, the default), beta (early access once a release has baked), or canary (bleeding edge, for builders who want every change first). Switch anytime — your memory and your clone stay exactly as they are, a track change only decides which updates you receive.

Try: run /klyr:channel to see your current track, or /klyr:channel beta to move up.</description>
  </item>
  <item>
    <title>Klyr's memory helper keeps itself up to date</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-26-self-updating-helper</guid>
    <pubDate>Sun, 26 Jul 2026 09:00:00 GMT</pubDate>
    <description>The background helper that runs your clone's memory now updates itself. You set it up once, and after that it keeps pace on its own — no command to run, no version to chase. Improvements reach you quietly, without an update dance.

Try: nothing to do — it's automatic.</description>
  </item>
  <item>
    <title>Your recent conversations are remembered sooner</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-25-conversations-remembered-sooner</guid>
    <pubDate>Sat, 25 Jul 2026 09:00:00 GMT</pubDate>
    <description>Your clone now picks up what you discuss as you go, not only when you close the session. Bring up something from a chat a few minutes ago — even from a different session — and it's already there to recall, instead of waiting until you're done. Your recent context stops living in a session you haven't closed yet.

Try: in a new session, ask your clone about something you talked through a few minutes earlier elsewhere.</description>
  </item>
  <item>
    <title>Your memory follows you to any Claude surface</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-24-memory-any-surface</guid>
    <pubDate>Fri, 24 Jul 2026 09:00:00 GMT</pubDate>
    <description>Your clone's memory is now reachable from any Claude surface — including a browser where Klyr can't see a single file on your machine. Add Klyr as a connector once, and from your phone, Claude Desktop, or a cloud code session you can ask what you've built together and it recalls. Nothing to install on that surface.

Try: open Claude in your browser, connect Klyr, and ask it what it remembers about a recent topic.</description>
  </item>
  <item>
    <title>Your clone can now talk to another member's clone</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-20-clone-to-clone</guid>
    <pubDate>Mon, 20 Jul 2026 09:00:00 GMT</pubDate>
    <description>Introduce yourself to a fellow member and your two clones exchange context — with both of you in control of what's shared. No group thread to manage, no copy-paste of who-knows-what. Your clone brings you up to speed on them, theirs does the same for you.

Try: ask your clone to invite a fellow member, then let them accept from their side.</description>
  </item>
  <item>
    <title>Ask for help right inside Klyr</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-20-help-chat</guid>
    <pubDate>Mon, 20 Jul 2026 09:00:00 GMT</pubDate>
    <description>Stuck on something? You no longer leave to find an answer. Ask your clone how to do it and it walks you through — setup, imports, what a command does — in your own words, in context.

Try: ask &quot;how do I connect my Google Drive?&quot; and follow along.</description>
  </item>
  <item>
    <title>Clean up a wrong import in one ask</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-19-cleanup-self-service</guid>
    <pubDate>Sun, 19 Jul 2026 09:00:00 GMT</pubDate>
    <description>Imported the wrong thing, or something landed under the wrong label? Ask your clone to fix it. It counts what would change first, shows you, and only deletes once you confirm. Your memory stays yours to curate — no support ticket, no waiting.

Try: ask &quot;what did that last import bring in?&quot; and clean up anything that doesn't belong.</description>
  </item>
  <item>
    <title>Your Google Drive, quietly kept in your clone's memory</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-19-drive-sync</guid>
    <pubDate>Sun, 19 Jul 2026 09:00:00 GMT</pubDate>
    <description>Point Klyr at the Drive folders that matter and it keeps them in sync on your schedule — every 15 minutes, hourly, or daily, your call. Read-only, nothing streams anywhere it shouldn't, and a first big sync drains fast in the background instead of blocking you. You keep working; your clone stays current.

Try: run the connector setup, pick a folder or two, and choose a cadence.</description>
  </item>
  <item>
    <title>Leave anytime, with everything</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-18-export-window</guid>
    <pubDate>Sat, 18 Jul 2026 09:00:00 GMT</pubDate>
    <description>If you ever cancel, you get a 30-day window from the end of your paid period to export all of your memory before it's permanently deleted. No lock-in, no games — your data is yours to take with you.

Try: nothing needed. It's how Klyr works, so you never have to worry about it.</description>
  </item>
  <item>
    <title>A status check that tells you the truth</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-18-honest-status</guid>
    <pubDate>Sat, 18 Jul 2026 09:00:00 GMT</pubDate>
    <description>Ask Klyr how it's doing and you get a straight answer — what's working, and what isn't — instead of a green light that hides a problem. If something needs your attention, it says so plainly, and tells you the one thing to do about it.

Try: run a status check and see the honest picture.</description>
  </item>
  <item>
    <title>See where every memory came from, in plain words</title>
    <link>https://getklyr.ai/whats-new</link>
    <guid isPermaLink="false">whats-new:2026-07-18-memory-provenance</guid>
    <pubDate>Sat, 18 Jul 2026 09:00:00 GMT</pubDate>
    <description>Your memory now shows its sources — which import, which conversation, which document a piece of context came from — in language you can read, not internal codes. When something looks off, you can see why it's there and decide what to keep.

Try: ask your clone where it learned a particular fact about you or your work.</description>
  </item>
</channel>
</rss>
