What's new.
What your clone can do now that it couldn't before — newest first, in plain words.
October 18, 2026Your clone slows down instead of stopping when the month's AI allowance runs out
Your subscription now comes with a clear monthly AI allowance. We email you at 80% so nothing surprises you, and if you reach 100% your clone keeps working in slow mode until the 1st: memory updates, deep reasoning, imports and searches are paced, within a small daily allowance, and nothing you send is lost.
Try: nothing to set up. If you get close, the 80% email gives you the reset date, and a big import can be arranged through [email protected].
October 17, 2026Subscribing after your beta month keeps your clone
When your free beta month ends and you subscribe, you keep the clone you already have: its memory, its workspace and your sign-ins carry straight over. No second clone, nothing to reinstall, nothing to set up again.
It works even when someone else pays, such as your company's billing team: we confirm by hand that the subscription lands on your clone, and tell you once it does.
Try: pay with the personal link from your beta follow-up email, then keep working in Claude Code as usual. Your clone remembers everything from the beta.
October 16, 2026An install that did not happen now says so
When the Klyr installer could not be downloaded, the install command used to end quietly and drop you back at the prompt, exactly as if everything had worked. Nothing was installed, and nothing told you.
Now that case can no longer pass for a finished install. The command stops with "Klyr was NOT installed. Nothing was changed on this computer." and tells you what to do next: wait a few minutes and paste the same command again. A finished install still ends with its own closing line, "Klyr is installed and ready" (on Windows, "Klyr installed and ready"), so you can tell the two apart at a glance.
Try: paste the install command from the Getting started page and look at the last line in the window. "Klyr is installed and ready" (or "Klyr installed and ready" on Windows) means you are set; anything else, the Troubleshooting page has an entry for it.
October 16, 2026Signing in again picks up where your app left off
Your app remembers the connection it made to Klyr, even after a reinstall or a sign-in you never finished. If that connection had gone stale in the meantime, signing in again used to stop on a cryptic error page, and the only way out was to clear the app's saved connection by hand.
Now Klyr recognizes the old connection and the sign-in simply continues: you enter your email, click the link, and you are back. In the rare case it cannot, the page tells you in plain words how to give the app a fresh connection, instead of an error.
Try: after reinstalling Klyr, type /mcp, select klyr and choose Authenticate. The sign-in goes through even if your last one was weeks ago.
October 15, 2026Add a contact with the email you already know, and see them by name
Connecting your clone to someone else's no longer involves an address you have to look up, copy or share. You add a contact with their email, the one you already use to reach them, and that is the only way in: nobody can pick, reserve or change an address for their clone any more, so there is nothing to type and nothing to guess.
Your contacts see your clone under its own name, the one you gave it. Rename your clone and they see the new name; there is nothing else to update.
In your own list, every contact shows their clone's name. Next to the name you also see the email you typed, for the people you invited yourself. An email is only ever shown to the member who typed it: someone who invited you with your email sees the address they typed, and someone you invited never sees yours.
An invite you send shows in your list with the email you typed, waiting, until they accept (or for 30 days). It never tells you whether that address belongs to a Klyr member. Changed your mind? Withdraw it with the same email: that does not tell you either.
Contacts you are already connected to stay connected: nothing you set up is lost. They show by name.
Try: /klyr:contacts and add someone with their email address.
October 14, 2026One account, one clone, whichever machine or purchase it comes from
Your Klyr account is your clone. Until now a second purchase with the address you already use could create a second, empty clone and quietly point your sign-in at it, so two of your machines could end up talking to two different memories without either one knowing.
Now the address decides. Sign in from any machine, or buy again with the same address, and you land in the clone that address already has: same memory, same identity files. If you cancel and come back within the 30 days your data is kept, you get that same clone back with its memory, nothing to restore. After those 30 days the data is deleted, and a new subscription starts a new clone.
Ended up with two clones for one address before this change? Write to [email protected] and we join them into one.
Try: sign in with /klyr:login on a second machine and ask your clone what it remembers about you; it answers from the same memory as on your first machine.
October 14, 2026Your team admin decides which directors each member gets
Klyr for Teams takes its first step. A company can now have a team: every member keeps their own clone and their own memory, and one person, the team admin, decides which of Klyr's four directors (Finance/Admin, Operations, Marketing, Sales) each member's clone works with.
Directors are off by default for a team. Klyr turns them on for the team when it asks; then the admin assigns them per member, or gives none at all. A team always keeps at least one super admin, so it can never lock itself out. Nothing of your memory is ever part of the team record.
Try: if your company wants a Klyr team, write to [email protected] with the address of the person who will administer it. We create the team and name them its first admin.
October 13, 2026Your dashboard can now read what your clone learned, on a hosted account too
The Memory screen of the Klyr dashboard shows what your clone learned about you today and which of your notes sit close to each other. On a hosted account that part used to say it was not available yet: the memory lives on the Klyr service, and the dashboard had no way to ask it.
Now it does. Your clone asks the service for the newest things it concluded about you, and for each note's nearest notes, and the service answers with exactly that: no raw memory, no vectors, nothing of anyone else. Your read key is all it needs.
Try: open the dashboard (dashboard_open), go to Memory, and watch "learned today" fill in on your hosted account once your clone updates.
October 12, 2026Tell another body of your account which session should hear you
One Klyr account runs on several machines, and each machine can have several Claude Code sessions open. Until now a message to another body could name the machine, not the session, so it landed wherever that machine decided.
Now a message to self#<label> can name the session too. It lands in that session as a native cross-session message when it is open there, and otherwise in the session that was most recently in use on that machine.
Try: from one session, contact_send(to="self#mac", to_session="klyr-dev-mac", body="..."), and watch the message arrive in that session on the Mac.
October 9, 2026Drive Kloned from your clone in Claude Code
If your plan includes Kloned, your clone can now work in your Kloned workspace for you, from the Claude Code session you already have. No second connection, no new sign-in: Kloned's tools show up next to your memory tools, and Klyr proves who you are to Kloned without ever handing it your own sign-in.
Try: ask your clone "which creators am I following in Kloned, and which of their posts are outliers this week?"
October 9, 2026You can now see everything your clone has concluded about you
On hosted, you can now export what your clone has learned about you: the cards it keeps about you, and every conclusion it ever stored, each with its date. Not just the recent slice it uses while you work, all of it. You do it yourself with your own sign-in, and the export always tells you when it has everything. It only ever contains what was concluded about you.
Try: ask your clone "export what you believe about me to a file".
October 9, 2026Invite your assistant or ghost writer into Kloned
If your plan includes Kloned, you can now invite the people who write with you into your Kloned workspace by email. Someone without Klyr gets a free sign-in with no subscription, no memory and no clone. It gets them into the Kloned workspaces they are invited to, and it opens no Klyr memory.
The person you invite never joins your Klyr account, so they can never open your clone's memory.
Try: in Kloned, invite your assistant's email address. They get an email with a link to Kloned and sign in with Klyr.
October 7, 2026You can now export your own hosted conversation history, yourself
On hosted, every conversation your clone has learned from can now be exported with your own sign-in: each session you took part in, your turns and your clone's, oldest first, with their dates. You no longer need to write to us to get a copy. An export that stopped halfway always says so, and if your history changes while it runs, it tells you to start over instead of quietly leaving something out. It only ever contains your own sessions.
Try: ask your clone "export my conversation history to a file".
October 7, 2026You can now export your own hosted memory archive, yourself
On hosted, your dormant memory (your notes index, your conversation history and every import) can now be exported with your own sign-in. You no longer need to write to us to get a copy. Your clone pulls it out store by store, in the same format a local install writes, so the file is yours to keep or move to a self-hosted Klyr. An export that stopped halfway always says so, and it only ever contains your own entries.
This covers dormant memory. The dynamic layer, the living model of you, is not included yet.
Try: ask your clone "export my Fathom store to a file", or "export all my dormant memory to a file".
October 7, 2026If you leave, you are told the exact date your data is deleted
When a subscription ends, Klyr now emails your account address the same day: when your access stopped, the exact date your hosted memory will be permanently deleted, and how to get your full copy before then (reply to the email). Nothing is deleted unless that email is on record as sent to you, or you were told another way.
The best moment to take your copy is before your paid period ends: until then you can export your memory yourself, with your clone, without asking anyone.
Try: nothing needed. If you ever cancel, watch for the email from Klyr with your date.
September 30, 2026A message from another member's clone now reaches you while you work
If you let the heartbeat check your clone-to-clone mailbox, a new message no longer sits unseen until your next session. The session you are working in gets a one-line notice with who wrote and how many messages. When you are away, the local notification says the same, if you turned it on. A new session also opens with a line saying mail is waiting. Your clone never opens the message by itself: you decide when to read it. A session you started before this update gets the local notification instead, until you restart it.
One small fix around contacts too: if you give your clone someone's email where it needs their address, it now says so and points you to your contacts list, instead of telling you that person is not your contact.
Try: turn on the heartbeat's mail check with /klyr:heartbeat, then keep working in a session when a contact writes to you.
September 30, 2026Your heartbeat can now run agents you write, on your schedule
The heartbeat, Klyr's optional background helper, can now run agents you describe yourself: "every weekday at 7, prepare this list", "check that every hour". Your clone writes the agent with you, gives it only the tools the job needs, and the heartbeat runs it on its schedule while you are away. What it finds waits as a short note for your next session. If the agent is edited after you switched it on, it stops until you switch it on again, so it never runs something you did not approve. Each run uses your own Claude usage, and scheduled runs stop while the heartbeat is off. Your HEARTBEAT.md now lists every agent with its schedule, its tools and its last result. Lines you had written in it yourself are kept in HEARTBEAT.saved.md, and your clone offers to turn each one into an agent.
If you chose the local notification, it now tells you where a note came from and what it is about, such as an agent's name and "2 important", instead of a bare "a note is waiting". When there is nothing to name, it stays quiet.
Try: with the heartbeat on (/klyr:heartbeat), tell your clone "every morning at 8, check X and tell me when Y happens". To check the notification still gets through, say "test my notifications again".
September 30, 2026PDFs and Word, Excel and PowerPoint files now open in the Klyr window
If you set up the Klyr window (the launcher that opens your notes folder in its own editor profile), a PDF, a Word document, a spreadsheet or a slide deck in your workspace now opens there as a readable view. Before, the window could only show you that the file was not text. The viewer's usage reporting is switched off, and long file names in the sidebar now scroll sideways instead of being cut. Old .doc and .ppt files are not covered yet.
Try: run /klyr:repair, then open a PDF or a .docx from your workspace in the Klyr window. If it still does not open as a document, ask your clone to set up the Klyr window again.
September 30, 2026Your clone now works like a chief of staff
Your clone keeps the conversation with you and hands the doing (file changes, commands, anything that goes outside) to helper agents. It briefs them with your standing rules, checks what they bring back before reporting it to you, and leaves anything that goes out to other people as your call.
If you already have a clone, /klyr:repair adds this as one new principle at the end of its core truths in your SOUL.md. It keeps a backup of the file first and changes nothing else. If you already wrote a principle with that title, nothing is added. If you delete it, it is not added back.
Try: run /klyr:repair, open your SOUL.md and read the "Chief of staff" line. Keep it, reword it, or delete it.
September 26, 2026On Windows without Git, the Git step the installer asks for now runs
When a Windows PC has no Git, the Klyr installer stops and asks you to run one line in an administrator PowerShell to install it. That line was refused with an authentication error, so the install could not go further. It now downloads and installs Git for Windows, with no sign-in needed.
Try: on a Windows PC without Git, run the install command in an ordinary PowerShell, then paste the line it prints into a PowerShell opened with "Run as administrator".
September 25, 2026Your clone can now file your inbox notes, even with no folders set up
If you asked your clone to keep your workspace tidy, it used to move a note only when its tag or name matched a folder you already had. Most members have no such folders, so most notes just waited. Now your clone reads each unfiled note and files it: into a folder you already have, or into a new, clearly named one. Every run is recorded, and one request undoes it, removing any folder it created once it is empty. A filing you undid is never repeated.
This filing runs with the heartbeat, Klyr's optional background helper. It now also works on Windows, and on Linux without Homebrew: the small tool it depends on is installed for you, and /klyr:status says plainly whether filing is ready.
Try: turn on tidy filing with /klyr:config and the heartbeat with /klyr:heartbeat. To reverse a run, say "undo the last filing run".
September 25, 2026Your clone looks it up before asking you
When your clone was about to end a turn by asking you for a fact, such as who, when, how much or where, without having searched for it, it now goes back once and looks first: your memory, your meetings, your mail and calendar, connected business systems and the web. If it still asks, it tells you what it searched and what it found.
Questions that are really decisions ("do you want me to…", "shall I…") still reach you as asked. This is on by default, and you can turn it off.
Try: ask your clone something whose answer is in your own notes. To turn this off, tell /klyr:config "let it just ask me".
September 25, 2026Open your notes in the Klyr window
Setup used to end by handing you a folder path. On macOS and Windows, your clone can now give you a way in: a Klyr launcher that opens your notes folder in your code editor, in its own Klyr profile set up for reading and writing notes. Your other folders and your usual editor setup are left as they are. Klyr does not install an editor; it uses the one you have.
The Klyr window opens light, and your clone's own theme, Klyr Light, matches it inside Claude Code there. A reopened window restores your terminal tabs without restarting old sessions in them. Anything Klyr set up can be removed again, and settings you chose yourself are never overwritten.
Try: ask your clone "set up the Klyr window". If the text looks washed out or you prefer dark, ask it to switch the Klyr window's theme.
September 25, 2026Your agents' background sessions no longer crowd out your own notes
When you ask your clone to recall something, sessions your background agents ran now count at half weight. They are still searched and can still come up, but an agent's transcript that happens to use the same words no longer pushes a note you wrote yourself off the list.
A recall that comes up empty is also no longer read as proof you never wrote it down. Your clone now knows a recent note may simply not be indexed yet, and says so instead of telling you there is no record.
Try: ask your clone about something you noted today. If it finds nothing, it now tells you the note may not be indexed yet.
September 24, 2026Local memory runs natively on Windows
You can keep your clone's memory on a Windows PC, the same way as on a Mac or a Linux machine. Klyr runs natively on Windows for this: nothing to run it inside, no second system to manage. What local memory needs is Docker Desktop, left on Linux containers, its default. Docker sets up whatever it needs on its own side.
Klyr's machine check on Windows also stopped telling you your graphics card was too weak. It cannot measure the card there yet, and it now says exactly that instead of guessing. Then it asks you whether your machine is capable and takes your word for it, so you can carry on with Local.
Local memory still needs a strong machine, on every platform. Hosted memory needs none of this.
Try: run /klyr:init, choose Local, and read the machine check. On Windows it now tells you what it could not measure and asks you, instead of blaming your graphics card.
September 24, 2026When memory cannot be reached, your clone says so instead of "no memory yet"
If your memory service had a problem, your clone could answer as if your memory were simply empty. That looked exactly like losing everything. Now an outage is reported as an outage: your clone tells you it could not reach your memory, says plainly that this is not an empty memory, names which part failed, and points you to /klyr:status.
A search where one source failed and the others found nothing no longer comes back as "nothing found" either.
Try: nothing to do. If your clone ever says it could not reach your memory, run /klyr:status to see which part is down.
September 12, 2026When something is off, one command puts it right
Klyr updates itself in the background, so you do not need a command to receive changes. What you sometimes need is a fix when something has drifted. That command is now called /klyr:repair: it checks your install, repairs what has drifted and cleans up old files. /klyr:update still works and does exactly the same thing.
Running the install command again now also gets you the latest release on your track. Before, it could hand back the older release already on your machine, the very one that was not starting. An older install that still kept its settings in a previous location is also moved over automatically, so your settings and onboarding answers come with you.
Try: if something looks wrong in /klyr:status, run /klyr:repair.
September 4, 2026Ask a contact's clone a question, and get an answer from their side
On hosted Klyr, your clone can now put a question to a contact's clone and bring back the answer. The answer is written on their side, from their memory, and only the answer crosses: no documents, no files, no list of sources.
It only works if they said yes. Being connected is not enough: each member decides, contact by contact, whose clone may question theirs, and can take that back at any time without disconnecting. If you ask someone who has not said yes, you get the same polite refusal whatever the reason, so no one can tell anything about them from it.
Try: /klyr:contacts, then "let ask my clone questions", or "ask 's clone what they think of X".
September 3, 2026Your clone has its own address, without you having to invent one
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.
August 11, 2026Your Drive copy now follows your moves, renames and deletions
When you moved, renamed or deleted a Google Doc, the copy your clone keeps could stay behind at its old place. Your clone could then find an old version and present it as current. The Drive sync now follows those changes: a moved Doc moves, a renamed one is renamed, and a deleted one leaves your clone's copy too.
Each copied note also now carries the id of the Doc it came from, so anything reading your notes can trace it back to the original.
Try: rename a Doc in a folder you sync, wait for the next sync, and ask your clone about it by its new name.
August 11, 2026On Windows, Klyr now runs out of sight and comes back on its own
On Windows, Klyr's background helper used to run in a terminal window you could see. Closing that window stopped it, and your clone lost its memory until the next login. It now runs with no window at all. A machine that still had one open fixes itself the next time the helper starts.
If the helper stops for any reason, it now restarts on its own, instead of leaving you without memory until you log in again. It also cannot end up running twice.
The Windows install also got sturdier. It now really installs the background helper (some installs stopped before that step). And when something goes wrong, it shows you the error instead of closing your terminal.
Try: nothing to do. If you ever closed a Klyr window on Windows, run /klyr:status to confirm memory is connected.
August 6, 2026The install page now tells the truth about your machine
Two 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 without saying what it needs: the memory engine runs in Linux containers, so self-hosting there requires Docker Desktop. The page says so now, where you make the choice, instead of after.
Try: if an install ever stopped on you, run the command on /docs/getting-started again.
August 4, 2026Your clone starts with sensible ground rules, and tells you when it is losing track of you
A new clone no longer starts from blank headings. It comes with working rules: say what it knows and what it does not, ask only when the answer changes the work, report what actually happened, and confirm before anything that leaves your machine or is hard to undo. You do not need to be good at writing prompts to get a clone that behaves well.
If your clone was set up before, nothing in your file changed. Your clone can show you each of these rules and add only the ones you pick, at the end of the right section, with a backup first. It never rewrites a line you wrote.
Your clone also reminds you when it has been a long time since it last interviewed you (every 90 days by default), because what it knows about you goes stale. You can change that interval or turn the reminder off.
Try: ask your clone "show me the default rules you can add to my profile". To change the reminder, ask your clone through /klyr:config.
August 4, 2026Two reviewers now come with your clone
Your clone ships with two helpers you can call on any time. The devil's advocate takes a plan, a decision or a claim and makes the strongest case against it, then tells you what would have to be true for it to fail. The cold reviewer reads something you are about to send exactly as the person receiving it will, with no knowledge of the conversation behind it, and tells you what they would misread or push back on.
Both only read and report. They never decide for you and never rewrite your work. And both are allowed to say nothing is wrong, so when they do raise something, it is worth reading.
Try: before you send your next proposal, tell your clone "read this cold". Before your next big decision, say "play devil's advocate".
August 4, 2026One browser sign-in sets up everything
Installing hosted Klyr used to need two sign-ins: one for the install, then a second one inside Claude Code before your clone could reach your memory. Now the install's single browser sign-in covers both. Your clone connects to your memory straight away, with no extra step.
Running the install again on a machine that is already signed in no longer sends you back to the browser either. It checks that your sign-in still works and carries on.
Try: run the install command from /docs/getting-started again. If you are already signed in, it skips the browser.
August 4, 2026Your clone recalls what fits the question you just asked
On hosted memory, your clone now reads what you type before it answers and pulls in the notes and past sessions that match it. Before, it started each turn with the same general context, whatever you asked. Now a question about a client or a project brings back what you wrote about that client or project, in the same turn.
Short messages and slash commands still take the fast path, so nothing slows down when there is nothing to look up.
Try: ask your clone about something you wrote down weeks ago, by name, and see it answer from your own notes.
July 27, 2026Know whether a memory is a draft or something you've confirmed
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.
July 27, 2026Choose how early you get new features
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.
July 26, 2026Klyr's memory helper keeps itself up to date
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.
July 25, 2026Your recent conversations are remembered sooner
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.
July 24, 2026Your memory follows you to any Claude surface
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.
July 20, 2026Your clone can now talk to another member's clone
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.
July 19, 2026Clean up a wrong import in one ask
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 "what did that last import bring in?" and clean up anything that doesn't belong.
July 19, 2026Your Google Drive, quietly kept in your clone's memory
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.
July 18, 2026Leave anytime, with everything
If you ever cancel, you get a 30-day window from the end of your paid period to get a full export of your memory before it's permanently deleted. During that window the export is sent on request; while your subscription runs, you can export it yourself. No lock-in, no games — your data is yours to take with you.
Try: nothing needed today. If you cancel, we email you the date your window closes and how to get your copy.
July 18, 2026A status check that tells you the truth
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.
July 18, 2026See where every memory came from, in plain words
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.