Changelog

What’s new with Murph

Seven days of features and improvements from the full Murph archive.

What's new in Murph

13 updates shipped in this edition.

Improvements

Improvement

Less work before replies

Reduced background bookkeeping while Murph prepares a reply.

Independent checks run together, and repeated checkpoint work is skipped while preserving your saved progress.

Improvement

Less silence before typing

Murph starts the typing indicator sooner after receiving a text message.

Typing can begin while Murph prepares your reply in private and supported group conversations.

Improvement

Simpler model choices

Choose Sol, Luna, or Astra in Settings without sorting through model versions.

Older models no longer appear as choices. Existing saved preferences stay in place until you change them.

Improvement

A simpler sidebar

Voice no longer appears in the sidebar navigation.

The desktop sidebar and mobile menu now show the same shorter list of destinations.

Improvement

Clearer medical record imports

Medical record imports distinguish portal coverage limits from routine notices and label repeated items more accurately.

More text-based lab results can be saved with their original reference ranges. Dated observations without a supported measurement format are preserved as source notes. Document extraction excludes generic education and provider illustrations from medical facts. Uncertain records remain available for reference.

Improvement

Clearer updates when a task needs another try

In private conversations, Murph explains a failed step before safe recovery and can acknowledge a delayed link send.

When the text of a reply is accepted but its separate link send remains unresolved, Murph attempts one brief update while retrying the link. Successful requests stay quiet; updates do not invent an outage or a completion time.

Improvement

Device updates keep moving

Connected-device updates avoid unnecessary pauses when background work receives a repeated wake-up.

New messages still take priority, while repeated background signals no longer stop a sync before it starts.

Improvement

Event lists stay focused

Review saved events even when unrelated saved records are malformed.

Event filters and corrections stay intact. Listing events does not require rebuilding unrelated summaries or search data.

Improvement

More useful follow-ups

Calendar plans stay useful context without automatically prompting an attendance check.

Automatic follow-ups focus on a specific health question. Reminders you explicitly requested are preserved, and older generic check-ins are skipped.

Improvement

Cleaner image replies in iMessage

Image replies no longer add a separate image description to the message.

Murph keeps the written reply and image together without automatically inserting the image's alt text as another paragraph.

Improvement

Fewer delays accepting iMessages

Murph avoids one cause of unnecessary retry delays when a private iMessage arrives during other account activity.

Account and conversation checks still apply before a message is accepted.

Improvement

Clearer destinations for lodging plans

Murph checks booking details before using a lodging destination in your travel context.

When a confirmation does not establish the destination, Murph keeps the confirmed dates and marks the location as unknown. Existing imported plans can be corrected when their booking details support a change.

Improvement

Medical records, easier to scan

See your latest import outcome and open lab results from a simpler medical records page.

Import details and connection controls sit together under Manage. Incomplete imports stay visible, and Data & privacy remains within reach.

What's new in Murph

12 updates shipped in this edition.

Improvements

Improvement

Fewer interrupted replies during updates

Murph can finish an active reply while a service update is rolling out.

Routine updates allow the conversation work to finish before the old runtime exits, reducing avoidable restarts and reply delays.

Improvement

More focused support summaries

Murph keeps support reports focused on the product problem while leaving out private health and family details.

Improvement

Less repeat work during Garmin imports

Garmin history imports combine overlapping requests for steps, distance, active calories, and breathing rate to avoid fetching the same days repeatedly.

Imports keep their full date coverage and can resume after an interruption. Completion time still depends on the amount of history and provider response time.

Improvement

Add Murph to your contacts after signup

Murph shares its contact card after your first delivered iMessage, whether you start by texting or sign up through the app or website.

Sharing follows delivered iMessage activity, with at most one automatic attempt per day. Your iPhone controls when it offers to save the contact. Accounts without an iMessage connection wait until one is established.

Improvement

Less waiting when you send a message

Murph does less startup work before processing a message when its messaging service starts fresh.

The change keeps the same encryption checks and message handling. Response times still depend on service and network conditions.

Improvement

More time to recover Personal Patterns updates

Daily Personal Patterns updates can recover from longer temporary service shortages.

Murph can retry the daily review for up to four hours after its scheduled time. Ordinary reminders keep their existing delivery window.

Improvement

A quicker introduction

Murph can acknowledge your name and move to your first health question through the quick reply path.

Partial answers and skipped identity details work too. If you already have a health goal or need help with something, Murph continues from that context. Your conversation stays intact, and your details carry forward as you continue.

Improvement

Save a plan without adding reminders

Murph can save an accepted walking or habit plan around a cue like before lunch, without asking for an exact clock time when reminders are off.

The saved plan stays linked to your goal. Choosing quiet support keeps reminders off, and you can ask to change or pause the plan. If you shift the start, a quiet plan’s relative first-week review moves with it.

Improvement

Lasting corrections carry forward

Corrections meant for future behavior are saved in the right place before Murph confirms them.

Changes scoped to one task stay with that task; broader reply preferences use your settings. One-off edits leave saved preferences unchanged.

Improvement

Keep chatting while group data updates

Murph can start answering new messages while shared group data updates in the background.

Sharing continues when a new message arrives, using saved data and your existing sharing permissions.

Improvement

Less repetition when logging workouts

Murph uses your saved workout duration and repetition instructions more consistently when you report later activity.

A duration you give for the current workout overrides your default. Repetition instructions apply only to the workout and exercise you chose, and a cleared instruction stays cleared.

Improvement

Voice stays connected during background work

A voice request can interrupt background work without disconnecting your call.

Murph can answer and continue the conversation on the same call while keeping background work under its existing controls.

What's new in Murph

12 updates shipped in this edition.

Improvements

Improvement

A gentle check-in during setup

If your introduction goes quiet, Murph can check in once to help you pick it back up.

The check runs about fifteen minutes after your introduction starts. It stays quiet if setup is complete, the latest setup question has not been unanswered for ten minutes, or you asked to pause or continue later.

Improvement

GPT-6 for opening replies and reminders

Murph uses GPT-6 Luna for quick opening replies and simple reminders, with GPT-6 Sol for reminders that need more context.

Managed check-ins and insights now use GPT-6 defaults. Existing OpenAI reminders already move to the corresponding GPT-6 model when they run; your conversation model and supported alternative-provider choices stay available.

Improvement

A quieter introduction

Murph no longer sets up an immediate follow-up nudge during your introduction.

Share or skip the opening identity question and continue the conversation. Later onboarding recovery keeps its existing schedule.

Improvement

Existing reminders follow model upgrades

Reminders and automations saved with GPT-5.6 Luna, Sol, or Terra now use their GPT-6 replacements when they run on OpenAI.

Luna moves to GPT-6 Luna; Sol and Terra move to GPT-6 Sol. Schedules and explicit reasoning settings stay intact, with no need to recreate reminders. Venice and custom-provider selections keep their existing behavior.

Improvement

Fewer startup delays

Murph can get started sooner when several conversations begin close together.

This reduces avoidable setup delays before a reply. Some conversations may still need extra startup time.

Improvement

Priority replies on your first day

Murph gives your personal conversations priority processing during your first 24 hours, at no extra cost.

Available with supported OpenAI models through Murph. The boost uses your normal AI allowance rate and ends automatically after your first day. Custom providers keep their existing processing.

Improvement

Less waiting when a conversation resumes

Messages can start processing sooner after background work has finished.

Murph skips an unnecessary retry delay when handing completed background work back to a conversation.

Improvement

Less preparation before replies

Messages take a shorter preparation path before Murph starts composing a reply.

Removes repeated setup while preserving conversation context and the order of pending replies.

Improvement

Less setup before replies

Murph does less setup when checking for new messages.

Family-sponsored conversations also avoid a repeated allowance lookup. Plans and usage limits keep their existing behavior.

Improvement

Less waiting between replies

Murph spends less time handing off from one conversation turn to the next.

This removes an avoidable pause when your next message arrives as the previous turn finishes.

Improvement

Plans with follow-through

When a private conversation leads to a repeated-action plan, Murph offers practical reminders and a check-in to help you follow through.

You can accept, adjust, or decline the support. Murph reuses timing you have already shared and asks about timing when needed before scheduling.

Improvement

Smoother setup after starting over

If you delete your account and start again in the same iMessage chat, old setup replies no longer prevent the quick opening questions.

What's new in Murph

11 updates shipped in this edition.

New features

Feature

Murph can vote and follow up on polls

Murph can cast or remove its own vote in iMessage polls it creates, including a playful pick or a tie-breaker.

Murph uses its judgment about when to participate. It can also notice a majority, everyone voting, or a closed Telegram poll and briefly acknowledge the result when useful. Telegram bots cannot cast native votes, so Murph can share a preference in the chat without changing the count.

Improvements

Improvement

Clearer participant labels in group reports

Group reports keep each person's shared results distinguishable when a profile name is missing or shared by someone else.

Murph can use a safe contact name shared by the group owner or a stable participant label when no name is available. Reports do not expose phone numbers or email addresses.

Improvement

More reliable workout corrections

Workout corrections preserve the original finish time, and workout cards remain readable in older Messages extensions.

Active cards keep their editing controls and completed cards keep their summary. If Murph cannot prepare a verified card, it replies with the saved workout details instead.

Improvement

Fewer detours before food and group replies

Murph takes fewer setup steps when looking up food labels or checking data shared with a group.

Food lookups recover more directly from command mistakes, and shared-data questions can skip a discovery step. Group replies continue to use only data members have chosen to share.

Improvement

Fewer avoidable pauses before replies

Murph keeps a ready session available while an incoming message is being handed off for processing.

This avoids an unnecessary restart during that handoff. Normal idle cleanup and recovery still apply.

Improvement

GPT-6 Sol is the new default

Murph uses GPT-6 Sol by default for managed OpenAI chats, with GPT-6 Luna also available to choose.

Terra selections now use GPT-6 Sol. Other saved model choices stay in place. Choose GPT-6 Sol or the lower-cost GPT-6 Luna in Settings, or ask Murph to switch.

Improvement

Lighter sign-in emails

Sign-in emails carry 40% less logo image data at the same resolution.

The light and dark logos stay embedded in the email. Display timing still depends on your mail app.

Improvement

Device history catches up with less repeated work

Large device history imports reuse repeated checks and move through dates with no readings with fewer interruptions.

Every historical day remains covered, with current connection checks before saving data and the same priority for new readings and messages.

Improvement

More reliable Journal capture and follow-ups

Completed actions and reported feelings are saved in the forms Personal Patterns can use, and calendar plans can recover a missing check-in.

Unscored symptoms stay unscored. Existing notification history and mutes are preserved, and recovery does not restart paused or completed check-ins.

Improvement

Morning checks keep reminders up to date

Murph reviews existing reminders against current context and repairs supported mistakes.

Morning checks can update stale instructions, follow changed event times, and retire confirmed obsolete or duplicate reminders. Explicit timing choices and delivery destinations are preserved. Outdoor reminders also check current travel context before choosing weather.

Improvement

Updated top-up usage allowances

New top-ups allocate 80% of the purchase price to AI usage, matching paid plans.

Purchase prices stay the same: $5, $10, $20, and $25 purchases provide $4, $8, $16, and $20 of metered usage capacity. This also applies to Family top-ups, group contributions, and new automatic group refills. Existing balances and purchases already started keep their original usage amounts.

What's new in Murph

11 updates shipped in this edition.

New features

Feature

Create polls with Murph

Ask Murph to create a native poll in your current iMessage or Telegram conversation, then ask it for the results.

Murph can find polls it created in that conversation. iMessage polls show voter handles and allow multiple choices. Telegram supports anonymous or named voting, uses one choice, and can be closed on request. Ask who voted on a named poll; Telegram totals and voter details reflect the updates Murph has received.

Feature

Talk with Murph on the website

Open Voice to speak with your Murph assistant and hear its answers, with readable captions, mute, and end-call controls.

Your microphone starts only when you choose Start call. Calls count toward your AI usage. Leaving the page ends the call; work Murph has already accepted can finish afterward. Requested reminders arrive through your connected messaging channel, which Murph names when confirming them.

Improvements

Improvement

More reliable dates for imported records

New medical-record imports check supporting dates before adding extracted events to your health history.

If an extracted date is missing or conflicts with its evidence, Murph checks the source again and corrects it when supported. Other valid records keep importing. Dates the source cannot establish stay out of dated summaries, and original documents remain available.

Improvement

Less repeated work when a conversation resumes

Murph can begin responding sooner when it already has the messages needed to resume your conversation.

Startup can reuse messages already fetched when a duplicate wake arrives. Newer messages and uncertain work still get a fresh check. Reply times continue to vary.

Improvement

Answers after a delegated lookup

When you ask Murph to delegate a lookup, it waits for the result before finishing its answer.

Independent saves during onboarding still happen in the background so the conversation can continue. If the lookup cannot finish, Murph explains the blocker.

Improvement

Device imports resume more reliably after updates

Device imports keep their saved progress when a Murph service update interrupts background work.

Unfinished work remains queued for the next run, without repeating imports that were already saved.

Improvement

Less background work when an experiment ends

Murph skips unrelated background work when analyzing and saving experiment results.

Results still use current health evidence. Rechecking an already saved result reuses that result without repeating the analysis.

Improvement

Less setup between messages

Murph can begin responding sooner in established conversations by reusing recent message preparation.

Messages stay encrypted, and each message still checks current access and conversation ownership. New or changed conversations receive fresh preparation. Reply times continue to vary.

Improvement

Less waiting behind background saves

New messages can interrupt a background save so Murph can begin responding sooner.

Work in progress stays available for a later save. A save already being committed finishes safely before the message continues.

Improvement

Less redundant oxygen history

Murph keeps oxygen readings and current analytics without generating the older duplicate set of oxygen statistics.

Untouched older statistics leave default searches and metric queries. Original evidence and records with later revisions remain intact.

Improvement

Personal Patterns checks spread throughout the day

Murph now gives each member a stable daily time for background Personal Patterns checks, reducing the shared midday rush.

Existing default-time checks move to their new slot after any running work finishes, beginning the next local day. Custom times, paused checks, and reminders you schedule keep their timing.

What's new in Murph

9 updates shipped in this edition.

Improvements

Improvement

Fewer pauses in device history imports

Device history imports keep moving through dates with no readings without unnecessary pauses between batches.

Provider retry waits and priority for your conversations still apply. Import time depends on the history available from your device provider.

Improvement

Less startup work between replies

Murph skips unnecessary service initialization when saving conversation progress, reducing startup work that can delay a follow-up.

Background wake scheduling still runs when needed. This reduces one source of delay; network and reply-generation time can still vary.

Improvement

Fewer repeated health insights

Personal Patterns updates check earlier health notes before sharing a finding again.

Findings already covered by a weekly insight or recent conversation are kept quiet, while genuinely new findings remain eligible for an update.

Improvement

Less repeated background syncing

Connected-device sync combines nearby background checks and avoids repeating empty weight-history scans.

History still checks for late readings, and regular reconciliation remains available to catch updates missed by incoming notifications.

Improvement

Less work before your reply

Murph skips repeated preparation work before responding in individual and group chats.

Reply preparation and runtime startup reuse information already read while checking current permissions.

Improvement

More useful memory in everyday conversations

Murph can carry more of your established preferences and preferred ways of getting help into private conversations.

Regular memory maintenance now shortens wordy memories while preserving their meaning, dates, and exceptions. It can learn explicit preferences for how you want help. Memories are not automatically deleted just because they are old. Existing active memory maintenance picks up the improvement automatically.

Improvement

More direct meal logging

Murph takes fewer unnecessary steps when saving meals and checking a day’s food log.

When a restaurant lookup needs its official website, Murph follows the relevant nutrition link before falling back to an estimate. Your preferences about nutrition numbers still apply.

Improvement

Fewer duplicate device records

Connected-device sync keeps the same source identity when background processing restarts.

Repeated imports continue to refer to the same connected source, reducing duplicate records from unchanged readings. Existing records are preserved.

Improvement

Stronger protection for saved vaults

Murph keeps recent encrypted vault backups available for recovery and rejects replacements missing essential vault metadata.

Recent backups can remain available for up to seven days, subject to existing content-expiry rules. Account deletion still removes them. These protections apply to new backups and do not automatically recover previously missing files.

What's new in Murph

3 updates shipped in this edition.

Improvements

Improvement

Fewer steps from meal log to nutrition card

Murph can save a meal and prepare its daily nutrition summary together, reducing the work before your card is ready.

Meal-history reads also avoid an extra rebuild after new data arrives. Food lookups and missing details can still take additional time, and your number-tracking preferences still apply.

Improvement

More reliable saved vaults

Murph better protects saved vault contents when temporary files change during a backup.

If a file needed for the backup disappears while it is being collected, Murph rejects that backup instead of accepting an incomplete copy. This prevents this failure in new backups; it does not repair an earlier incomplete backup.

Improvement

More reliable follow-up replies

Follow-up messages can reuse a healthy reply connection after a pause in the conversation.

Connection recovery preserves the conversation when a provider connection closes.