← The 5 stories that mattered

Everything collected ·

All 366 items collected for this issue

New here? How to read this issue
  1. Read the picks. Each tab opens with 4–5 stories ranked by how much you’d regret missing them. That takes about 3 minutes. “Start the read” shows one story at a time, and “Listen” reads them aloud.
  2. Stop at “You’re caught up”, or go deeper. Everything after it is the full list of what was collected today, folded away.
  3. Android comes first. Product & AI covers what builders are launching and discussing.
Stable · Beta · Alpha
Release stages. Stable is safe to ship, beta’s API is frozen but may still have bugs, alpha is experimental.
AndroidX
Google’s Jetpack libraries (Compose, Paging, Room…), released separately from Android itself.
AOSP insider
Code changes merged into Android’s open source repository. They often show an API before it’s announced.
Lanes
Where an Android item comes from: official, AOSP insider, experts, open-source library releases, leaks and ecosystem, community.
Adopt now · Watch · Rumour
What to do about it, and how sure the source is.
Dotted underline
An inferred claim: Claude’s reading, not something the source says.

Collected automatically each morning from 37 sources. Notes are written by Claude. Links show what was trending, not endorsements.

Today’s Android picks

Start the Android read5 stories, ranked by what you’d regret missing · 2 min read
  1. Pick 1. DataStore 1.3.0 is stable with built-in encryption

    Why it matters: If you encrypt tokens or settings by hand on top of DataStore, you can now use a first-party option instead.

    Google released DataStore 1.3.0, the Jetpack library for storing settings and small data. A new artifact, datastore-tink, encrypts what you store using Google's Tink library. Kotlin Multiplatform apps get web storage backends. A new DataStore Builder replaces the old factory, the library now ships Baseline Profiles for faster startup, and a data-loss bug in the Guava variant is fixed.

  2. Pick 2. Grab cuts ANRs by a third with R8 and startup profiles

    Why it matters: It is hard numbers from a very large app, which helps justify the work of enabling full R8 and startup profiles in your own build.

    The Android Developers Blog published a case study from Grab, the Southeast Asian super app for rides, food and payments. After turning on R8, the code shrinker and optimizer, along with profile-guided optimization, Grab reports 32 percent fewer app-not-responding errors and 35 percent faster startup. Android Weekly also picked up the story this week.

  3. Pick 3. kotlinx.serialization 1.12.0 reaches stable

    Why it matters: Most Kotlin apps depend on this library, so a stable release matched to the current compiler is a safe upgrade to schedule.

    JetBrains released kotlinx.serialization 1.12.0, the official Kotlin library for turning objects into JSON and other formats. It is built on Kotlin 2.4.10 and includes every change from the release candidate, plus a fix that removes unnecessary leading whitespace in output. Projects already on Kotlin 2.4.10 can move to it without waiting.

  4. Pick 4. Where catch belongs in a Kotlin Flow

    Why it matters: Flow error handling sits in most repositories and ViewModels, so a misplaced catch is a crash waiting in many apps.

    A ProAndroidDev post explains a common Kotlin Flow mistake. If you place catch after flowOn, or after another operator that adds a channel between producer and consumer, your fallback can be skipped or the app can crash. The author shows why this happens and where to put catch instead so errors are handled as you expect.

  5. Pick 5. Compose Multiplatform 1.12.2 fixes an iOS text crash

    Why it matters: If your multiplatform app on 1.12 has text input on iOS, this patch removes a crash with no migration work.

    JetBrains shipped Compose Multiplatform 1.12.2, a patch release for the shared UI toolkit. It fixes flickering when animating shadows on non-rectangular shapes, and an iOS crash when a text field lost focus. The next feature version, 1.13, is in beta and brings a binary-incompatible change for desktop libraries that use drag and drop.

Go deeper: every Android item, by lane

Official & releases

56
Adopt DataStore 1.3.0 for built-in encryption and read Grab's R8 and profile-guided optimization case study; Compose 1.13 is at beta02 and AppFunctions is in beta.
Show 7 more

AOSP / AndroidX insider

0

Nothing new here today.

Experts

19
Read the ProAndroidDev post on where catch belongs in a Flow, Chris Banes on Haze 2.0 and Compose's new blur, and skydoves' Compose mechanisms series.
Show 11 more

Library releases

6
kotlinx.serialization 1.12.0 is stable and safe to adopt on Kotlin 2.4.10, Roborazzi 1.77.0 fixes configuration-cache reuse, and OkHttp 5.5.1 blocks compromised eMudhra certificates.
  • Patch Changes 9658157 : Support dismissOnClickOutside for DrawerPresentation.InPlace

  • Version 5.5.1

  • Version 4.12.1

  • This release is based on Kotlin 2.4.10 and contains all of the changes from 1.12.0-RC . Additionally, it includes a fix removing unnecessary leading whitespaces from Proguard rules ( #3270 ), and two changes stabilizing kotlin.uuid.Uuid serializer ( #3263 ) and…

  • What's Changed Library Add linuxX64 and linuxArm64 targets by @arkivanov-bot in #1028 Fix wrong directions in AndroidPredictiveBackAnimatableV1 in RTL layout by @arkivanov in #1030 Fix wrong directions in AndroidPredictiveBackAnimatableV2 in RTL layout by @arkivanov in #1031 Add…

  • Bugfix: verifyRoborazzi* and compareRoborazzi* reuse the configuration cache With the configuration cache enabled, the second verifyRoborazzi* or compareRoborazzi* run after clean recalculated the task graph because "the file system entry 'build/outputs/roborazzi' has been…

Leaks & ecosystem

16
OnePlus and Samsung are rolling Android 17 to phones, and Google will use Gmail and Photos data for ads when Personal Intelligence is on.
Show 8 more

Community

40
Hacker News is loud about Android TV without ads, microG and Android apps on macOS, while Android Weekly covers Gemini Nano's 4,000-token input limit and shipping a Gemma model through Play.
Show 32 more

Today’s Product & AI picks

Start the Product & AI read4 stories, ranked by what you’d regret missing · 2 min read
  1. Pick 1. VoiceStudio offers a fully local alternative to ElevenLabs

    Why it matters: Voice work no longer has to mean sending recordings to a cloud vendor, which changes the cost and privacy math for voice features.

    VoiceStudio is an open-source app that does voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation entirely on your own machine. It added about sixteen hundred stars on GitHub today and has around eighty-seven thousand in total. It positions itself directly as a local replacement for ElevenLabs, the popular paid voice service.

  2. Pick 2. Hurston-1 is an open TTS model for Southern and Afro-English

    Why it matters: It shows a small team can win a voice niche the large vendors ignore by training for a specific way of speaking.

    A developer open-sourced Hurston-1, a narrowband text-to-speech model under the Apache license. The author says it is very good with American English and especially good with Southern American and Afro-English, accents most commercial voices handle poorly. It appeared on both Show HN and the Hacker News front page.

  3. Pick 3. A root shell on Samsung TVs sparks a tracking debate

    Why it matters: On-device models make tracking cheap enough to run inside every TV, and users are noticing.

    The top Hacker News story today, with nearly eight hundred points and six hundred comments, describes getting a root shell on a Samsung TV. A merged thread claims the TV runs a TensorFlow Lite model on low-resolution screen images to track what viewers watch. The discussion covers how much smart TVs observe and how to stop it.

  4. Pick 4. Cloudflare's agent security audit skill keeps climbing

    Why it matters: A written audit method that any coding agent can follow is becoming the default way small teams get a security review.

    Cloudflare's security-audit-skill, which lets coding agents run a multi-phase security audit with independently verified, machine-readable findings, was the fastest-growing repository on GitHub for a second day. It added about twenty-nine hundred stars today and is near forty-seven thousand in total. Each finding is checked by a separate pass before it is reported.

Go deeper: themes, product notes, every source

Themes across sources

6
Open voice models · Coding-agent control surfaces · Verifying agent work · Agents as security auditors · Agent-ready Android · Anti-slop design skills

Ideas showing up in more than one place today. The line counts items per day over two weeks.

Open voice models

New · 6 items from 7 sources

Speech models you can run yourself are trending across sources at once. VoiceStudio, a fully local alternative to ElevenLabs for cloning, dubbing and transcription, added about 1,600 stars today; Hurston-1, an Apache-licensed TTS model tuned for Southern American and Afro-English, is on both Show HN and the front page; Fish Audio's Drama 3 trends on Hugging Face as a model and a demo. On the hosted side, ElevenLabs launched realtime voice agent models, and a Hugging Face paper has voice agents start work while the user is still talking.

Why now. Open speech models are now good enough for cloning and dubbing on a consumer GPU, so the privacy and cost case for local voice is finally practical.

debpalash/VoiceStudioGitHub Trending

Coding-agent control surfaces

Rising · 8 items from 3 sources

Tools for steering a fleet of coding agents keep arriving. JetBrains published Thinkrail, a lightweight IDE for vibe coding with the pi agent that adapts itself to how you work. Product Hunt still carries AgentValley in the Mac notch, Inyon for answering agents from your phone, Monish on the lock screen, Peras to pause agents before they burn your budget, and Termi Protocol, which shows agents coding in 3D. Agent Relay, a YC launch, lets a team's agents message each other.

Why now. Developers now run several long-lived agents at once, so supervising them, often away from the desk, is the new bottleneck.

JetBrains/thinkrailGitHub Trending

More on this

Verifying agent work

Steady · 7 items from 5 sources

Checking what agents produce is its own product category. Farol on Show HN draws a risk map of a pull request for the person who approves it, and another Show HN keeps deliberation records for human and AI work in Git. YC's Simulithic and Aucert send agents to test apps on real devices, Latent catches hallucinated answers, and DotMD reviews agent specs like a pull request.

Why now. Agents write code faster than people can read it, so review, not generation, limits how much teams can ship.

Show HN: Farol – A risk map of a pull request for the person who approves itShow HN

Agents as security auditors

Steady · 5 items from 5 sources

Security work keeps moving to agents. Cloudflare's security-audit-skill, a multi-phase audit with independently verified findings, was again the fastest-growing repo on GitHub, adding about 2,900 stars. A Show HN pitches an open-source platform where AI agents protect businesses, Armorer Labs verifies agents in regulated industries, and a Hugging Face paper shows agents can leak confidential conclusions by combining harmless documents.

Why now. Models can now read whole codebases and run tools in phases, so an audit method can be written down once and run on every repo.

cloudflare/security-audit-skillGitHub Trending

Agent-ready Android

Rising · 6 items from 4 sources

Android keeps adding the pieces agents need. AppFunctions, the API that lets assistants call into your app, is in beta and A2UI for agent-generated Compose UI is at its second alpha. Gemini 4 Argon is in Android Studio Canary through Antigravity with an Android CLI plugin, Google's Developer Knowledge API serves docs to assistants, and Android Weekly carries an AppFunctions explainer and part six of an on-device agents series.

Why now. Assistants on the phone can now plan multi-step tasks, so apps need a typed way to expose features to them.

Appfunctions 1.0.0-beta01AndroidX releases

Anti-slop design skills

Steady · 4 items from 2 sources

Taste and expertise are being packaged as agent skills. Hallmark, an anti-AI-slop design skill for Claude Code, Cursor and Codex, added about 1,300 stars today and Impeccable, a design language for agent harnesses, is near 88 thousand. Claude SEO bundles 26 sub-skills for search work, and a Lobsters post argues that AI skills are worthless in 2026.

Why now. Skills became a shared format across several coding agents, so one text file of rules can reach every tool at once.

Nutlope/hallmarkGitHub Trending

Fading: Agent sandboxes (last seen 2026-10-25) · Agent memory layers (last seen 2026-10-21) · Agent harnesses (last seen 2026-10-21) · Open-weight frontier models (last seen 2026-10-21) · Agent supply-chain safety (last seen 2026-10-21) · AI-found vulnerabilities (last seen 2026-10-21) · On-device AI (last seen 2026-10-19)

Product notes

15
Who each product is for, the problem, why now, its wedge and how it makes money. Today’s picks first.

Plain text: the source says soDotted: inferred

debpalash/VoiceStudio

repoGitHub Trending★ 1,592 today

What
VoiceStudio, an open-source, fully local alternative to ElevenLabs for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation.
For whom
Creators and developers who need voice work done without sending recordings to a cloud service or paying per character.
Problem
Hosted voice tools charge by usage and hold your voice data; people cope by paying, or by stitching together several open models by hand.
Why now
Open speech models now reach usable quality on consumer GPUs, which was not true two years ago.
Wedge
One app that bundles many voice jobs under a name people already know, the local ElevenLabs.
Money
Open source, no model yet.
Like
ElevenLabs · Coqui TTS · Fish Audio · Whisper

LessonPositioning against a known paid product tells users exactly what you replace in four words.

Show HN: Hurston-1 open source TTS that speak Southern American and Afro-English

productShow HN, HN front page48 pts · 23 comments

What
Hurston-1, an Apache-2.0 narrowband text-to-speech model that is strong on American English and especially on Southern American and Afro-English.
For whom
Developers building voice products for speakers and audiences that mainstream TTS voices underserve.
Problem
Most TTS voices default to one standard accent, so products sound foreign to many of their own users.
Why now
Training a usable TTS model is now cheap enough for one person to target a specific dialect.
Wedge
A dialect focus no large vendor prioritizes, with a permissive license.
Money
Open source, no model yet.
Like
ElevenLabs · Piper · Kokoro

LessonA narrow audience the big players ignore is a better first market than a slightly better general model.

cloudflare/security-audit-skill

repoGitHub Trending★ 2,878 today

What
A coding-agent skill from Cloudflare that runs a multi-phase security audit and produces independently verified, machine-readable findings.
For whom
Teams using Claude Code or similar agents who want a repeatable security pass without a dedicated security engineer.
Problem
Manual audits are slow and rare, and one-shot agent reviews produce noisy, unverified findings.
Why now
Agents can now read whole repositories and run tools in phases, and a skill file is enough to encode an audit method.
Wedge
Independent verification of each finding and machine-readable output that can feed CI.
Money
Open source, no model yet; Cloudflare gains goodwill and a path to its platform.
Like
Semgrep · Snyk · CodeQL

LessonPackage a process, not a prompt: the verification step is what makes agent output safe to automate on.

Show HN: Farol – A risk map of a pull request for the person who approves it

productShow HN60 pts · 37 comments

What
Farol draws a risk map of a pull request for the person who has to approve it.
For whom
Reviewers facing large pull requests, often written by agents, who need to know where to look first.
Problem
Reviewers read diffs top to bottom and spend equal time on trivial and dangerous changes.
Why now
Agent-written pull requests are larger and more frequent, so reviewer attention is the scarce resource.
Wedge
Built for the approver rather than the author, a role most code tools ignore.
Money
Not stated.
Like
CodeRabbit · Graphite · GitHub Copilot code review

LessonPick the person in the workflow nobody builds for; the approver has a different job from the author.

JetBrains/thinkrail

repoGitHub Trending★ 51 today

What
Thinkrail from JetBrains, a lightweight IDE for vibe coding with the pi agent that customizes itself around the way you work.
For whom
Developers who mostly direct an agent and find a full IDE too heavy, but want more than a chat window.
Problem
Full IDEs are built for typing code, and agent chat apps hide the code; people switch between both.
Why now
Agents now write most of the code in some workflows, so the editor's job shifts to steering and reviewing.
Wedge
A real IDE in a light shell, from a company developers already trust for IDEs.
Money
Not stated; likely tied to JetBrains subscriptions or AI usage later.
Like
Cursor · Zed · Claude Code · Fleet

LessonAn incumbent can answer a new workflow with a separate, lighter product instead of bolting it onto the flagship.

Nutlope/hallmark

repoGitHub Trending★ 1,317 today

What
Hallmark, an anti-AI-slop design skill for Claude Code, Cursor and Codex.
For whom
Developers using agent coding tools who want generated screens to avoid the recognizable AI look.
Problem
Generated interfaces share tells such as gradients, centered hero cards and filler copy that users now spot.
Why now
Skills became a standard way to extend several coding agents, so one file reaches three tools.
Wedge
Named against a widely felt problem, slop, rather than presented as a general style guide.
Money
Open source, no model yet.
Like
Impeccable · shadcn/ui

LessonNaming the pain users already have a word for does more than describing the feature.

ElevenLabs Realtime

productProduct Hunt#48 on Product Hunt

What
ElevenLabs Realtime, voice agent models with 570 milliseconds to first audio.
For whom
Teams building phone and app voice agents where a pause makes the conversation feel broken.
Problem
Chained speech-to-text, model and text-to-speech pipelines add seconds of delay; teams cope with filler sounds.
Why now
Voice agents are moving into support and sales, where latency is judged against a human.
Wedge
A single latency number as the headline.
Money
Usage-based API, in line with ElevenLabs' existing pricing.
Like
OpenAI Realtime API · Cartesia · Deepgram

LessonWhen quality is close across vendors, one measurable number becomes the product.

Pomerado - The faster, cheaper, and more reliable alternative to browser use

productYC Launches10 votesHype flag

What
Pomerado, an open-source way to connect agents to any website without an API, pitched as faster, cheaper and more reliable than browser use.
For whom
Teams whose agents must act on sites that have no API.
Problem
Screen-driving browser agents are slow and break on layout changes; teams cope with brittle scripts.
Why now
Agents are now expected to complete tasks on real sites, so the reliability of that layer decides whether they work.
Wedge
Open source and framed against a specific incumbent approach, browser use.
Money
Not stated; likely a hosted tier on top of the open-source core.
Like
Browser Use · Browserbase · Moli

Faster, cheaper and more reliable are claimed without figures in the listing.

LessonComparing yourself to a named alternative is clear only if you publish the numbers behind it.

Simulithic — AI users that test your app on every device and browser.

productYC Launches85 votes

What
Simulithic sends AI users through your app on every device and browser to verify code as fast as agents write it.
For whom
Web and mobile teams whose agents produce more changes than their test suite covers.
Problem
Cross-device bugs reach real users because device matrices are expensive to test by hand.
Why now
Agent-written code has raised change volume, and agent testers can explore a UI without scripted steps.
Wedge
Breadth of devices and browsers, pitched at teams already using coding agents.
Money
Not stated.
Like
Aucert · BrowserStack · Firebase Test Lab

LessonIf one new tool creates volume, the tool that absorbs that volume is the next product.

Agent Relay - Let your teams' coding agents message each other

productYC Launches15 votes

What
Agent Relay, real-time messaging so a team's coding agents such as Claude Code, Codex, Cursor and Conductor can message each other.
For whom
Teams where several engineers each run agents on the same codebase.
Problem
Agents work in isolation and learn about conflicts at merge time; people relay context by hand.
Why now
Several agents per team is now common, so coordination between them has a real cost.
Wedge
Works with any agent, which no single agent maker has reason to build.
Money
Not stated; likely per-seat SaaS.
Like
Slack · Conductor · Context Engine

LessonInteroperability between rivals is a durable wedge because none of the rivals will build it.

1Password for Agents

productProduct Hunt#19 on Product Hunt

What
1Password for Agents lets AI agents sign in to services for you without seeing your passwords.
For whom
People who run browser or desktop agents that need to log in to real accounts.
Problem
Agents either get pasted credentials, which leak into logs, or stop at every login screen.
Why now
Agents now act on accounts routinely, so credential handling is a daily problem.
Wedge
The vault people already trust brokers the session, so the agent never holds the secret.
Money
Not stated; likely part of 1Password subscriptions.
Like
Bitwarden · Browser Use · Orgo

LessonAn incumbent's trust can become the control point of a new workflow if it moves before the newcomers.

RikkaApps/Shizuku

repoGitHub Trending · KotlinAndroid★ 55 today

What
Shizuku lets ordinary Android apps call system APIs with adb or root privileges through a Java process started with app_process.
For whom
Power-user Android apps such as app managers, theming and automation tools, and the people who install them without rooting.
Problem
Many useful system APIs need privileges normal apps lack; the alternatives are rooting the phone or running adb commands by hand.
Why now
Wireless debugging on modern Android lets a phone grant adb-level access to itself, which makes the approach practical without a computer.
Wedge
One shared privileged service that many apps can use, instead of each app asking for root.
Money
Open source, no model yet.
Like
Magisk · LADB · Termux

LessonBecome the shared layer other apps build on, and their users become yours.

google-ai-edge/gallery

repoGitHub Trending · KotlinAndroid★ 18 today

What
Google AI Edge Gallery, an Android app that showcases on-device machine learning and generative AI and lets people try models locally.
For whom
Android developers deciding whether an on-device model is fast and good enough for their feature.
Problem
Judging on-device model quality means building a test app first; most teams guess or default to the cloud.
Why now
Phones can now run useful small models, and Android Weekly this week covers shipping a 584 megabyte Gemma model through Play.
Wedge
A working reference app from Google that runs models on your own phone.
Money
Open source; Google benefits when developers adopt its on-device stack.
Like
MLC Chat · PocketPal · Ollama

LessonA demo people can run on their own hardware convinces more than a benchmark table.

Haze 2.0

articleChris BanesAndroid

What
Haze 2.0, the Compose Multiplatform blur library, adds Glass, a new effects API, performance improvements and experimental support for Android's native backdrop.
For whom
Android and multiplatform developers building glass-like and blurred surfaces in Compose.
Problem
Compose had no cross-platform backdrop blur; now Compose's progressive blur and Android's backdrop API overlap with Haze.
Why now
The platform is shipping its own blur primitives, so Haze moves up to effects and to bridging the native backdrop.
Wedge
Already the default blur library in Compose; 2.0 wraps the new native APIs.
Money
Open source, no model yet.
Like
Compose progressive blur · Android backdrop API · Cloudy

LessonWhen the platform absorbs your feature, become the ergonomic layer over the platform's version.

Introducing Crayfish: An Image Cropper for Compose Multiplatform

articleDove Letter (skydoves)Android

What
Crayfish, an image cropper for Compose Multiplatform with a one-line crop dialog, a Cropper composable, aspect ratios, gestures, shapes and Coil support.
For whom
Compose and KMP developers who need image cropping without a View-based library.
Problem
Most Android croppers are old View libraries that do not work in Compose Multiplatform.
Why now
Compose Multiplatform is used in production on several platforms, so UI utilities need multiplatform versions.
Wedge
One line to get a crop dialog, plus Coil integration most Compose apps already have.
Money
Open source, no model yet.
Like
uCrop · Android-Image-Cropper · Landscapist

LessonEvery platform shift reopens the utility libraries; the first good version for the new toolkit wins by default.

By source

11
Everything collected today from GitHub Trending, Product Hunt, Show HN, HN front page, YC Launches, HF trending models, HF trending spaces, HF daily papers, Lobsters, Dev.to top, Techmeme, in each source’s own order.

GitHub Trending

11
  • Cindy, an open-source agent pitched as working out of the box, keeps trending with about five thousand stars.

    ★ 675 today

  • Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

    ★ 1,317 today

  • VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

    ★ 1,592 today

  • Impeccable, a design language for agent harnesses, is near 88 thousand stars as design taste becomes an installable file.

    ★ 1,092 today

  • A tiny open-source biped duck robot with a Hugging Face simulator, a cheap entry point to legged robotics.

    ★ 647 today

  • A multi-agent LLM framework that simulates a trading firm's roles; popular as a research demo of agent teams.

    ★ 381 today

  • An open-source Chinese astrology chart engine with its rules and source texts as data, a large hobbyist project.

    ★ 199 today

  • Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need

    ★ 51 today

Show 3 more
  • Coolify, the self-hostable alternative to Vercel, Heroku and Netlify, keeps growing past 64 thousand stars.

    ★ 152 today

  • A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

    ★ 2,878 today

  • An SEO skill for Claude Code with 26 sub-skills and 19 sub-agents, specialist know-how sold as an agent plugin.

    ★ 197 today

Product Hunt

50
  • Product observability for teams shipping with AI, watching what shipped rather than what was planned.

    #1 on Product Hunt

  • A shared workspace where humans and agents work side by side, another take on the agent control room.

    #2 on Product Hunt

  • A headless browser built for agent speed, pitched as the fastest option for harnesses.

    #3 on Product Hunt

  • Turns an iPhone into a name badge that faces the room, a small event utility.

    #4 on Product Hunt

  • Data rooms an AI agent can operate, applying agent access to a document-heavy deal workflow.

    #5 on Product Hunt

  • Generates lyric video ads timed to the beat for musicians, a vertical video tool.

    #6 on Product Hunt

  • A tiny Mac focus timer started by pulling a paw, a playful utility in a crowded category.

    #7 on Product Hunt

  • Explains why your MRR numbers differ between tools and gives one you can trust.

    #8 on Product Hunt

Show 42 more
  • AI podcast summaries with tap-to-jump timestamps inside Telegram, meeting listeners in a chat app.

    #9 on Product Hunt

  • A modern rework of the git-flow branching tool for teams that still use that model.

    #10 on Product Hunt

  • One local AI server that every Windows app can call, the on-device model as a shared system service.

    #11 on Product Hunt

  • Traces how a post went viral from the first share, analytics for creators and marketers.

    #12 on Product Hunt

  • Incident management sized for small teams, a lighter alternative to enterprise on-call tools.

    #13 on Product Hunt

  • Shows exactly how much data you use on every network, a plain usage meter.

    #14 on Product Hunt

  • A 1990s five-disc CD changer recreated for the iPhone Duo, a nostalgia app built for the new foldable.

    #15 on Product Hunt

  • Reclaims the disk space Xcode, Docker and node_modules consume.

    #16 on Product Hunt

  • Every Claude Code agent's status in the Mac notch, a glanceable control surface for parallel agents.

    #17 on Product Hunt

  • Canva turns prompts into editable, design-ready images, keeping AI output inside its editor.

    #18 on Product Hunt

  • Let AI agents sign in for you without seeing your passwords

    #19 on Product Hunt

  • Vibe-code, publish and monetize games with AI, a creator pipeline for casual games.

    #20 on Product Hunt

  • AI 3D generation that outputs manufacturable parts rather than meshes, aimed at engineers.

    #21 on Product Hunt

  • A quiet Mac writing app for screenplays and novels, a focused tool against bloated editors.

    #22 on Product Hunt

  • Restores Mac windows after sleep or replugging displays with zero clicks.

    #23 on Product Hunt

  • Delivers LinkedIn post analytics straight into your AI assistant.

    #24 on Product Hunt

  • Local AI for dictation, meetings and background tasks, everyday AI moving onto the device.

    #25 on Product Hunt

  • Turns a route, photos and clips into a short film, a consumer memory app.

    #26 on Product Hunt

  • Ask once and get a fresh CSV in Slack or email every week, scheduled exports for non-technical teams.

    #27 on Product Hunt

  • Pauses Claude Code and Codex before they burn your weekly budget, a spend guard for agent subscriptions.

    #28 on Product Hunt

  • An AI on-call engineer for Cloudflare apps, vertical agent ops for one platform.

    #29 on Product Hunt

  • Watch AI agents code in a 3D view and hand off work between them, agent supervision as a visual scene.

    #30 on Product Hunt

  • A personal AGI on your PC, a big claim with no stated wedge.

    #31 on Product Hunt

  • Dub's startup program for partner-led growth, a go-to-market offer rather than a product.

    #32 on Product Hunt

  • A phone-calling plugin for OpenAI's Dots, giving an assistant the ability to make calls.

    #33 on Product Hunt

  • Fast local AI search over your files, keeping file search on the device.

    #34 on Product Hunt

  • Your Mac on the iPhone Duo; fold it and a keyboard appears, an early app built around the new foldable.

    #35 on Product Hunt

  • One shared memory for AI agents and human teammates, memory as a team resource.

    #36 on Product Hunt

  • Review your agent's Markdown specs like a pull request, treating plans as reviewable code.

    #37 on Product Hunt

  • Live rankings of which tools AI agents use most, a leaderboard for the agent tool market.

    #38 on Product Hunt

  • See a product change live before it ships, preview environments for product teams.

    #39 on Product Hunt

  • Your AI agents live on the iPhone lock screen, agent status as a glanceable widget.

    #40 on Product Hunt

  • Fixes messy tags, covers and duplicates in a Mac music library.

    #41 on Product Hunt

  • A customizable workspace in the Mac notch, the notch as a new UI surface.

    #42 on Product Hunt

  • Cloudflare's own model for fast, cheap data extraction, infrastructure companies shipping task-specific models.

    #43 on Product Hunt

  • A private ChatGPT alternative that sets itself up on your Mac, local assistants for non-technical users.

    #44 on Product Hunt

  • Answer your coding agents' questions from your phone so long runs do not stall while you are away.

    #45 on Product Hunt

  • Use AI to defend against AI, a security pitch with no concrete mechanism in the listing.

    #46 on Product Hunt

  • FLUX 3 Max on fal generates ten seconds of video in about twelve seconds, near real-time video generation.

    #47 on Product Hunt

  • Realtime voice agent models with 570ms to first audio

    #48 on Product Hunt

  • A long-form video agent for mobile, generating full videos from the phone.

    #49 on Product Hunt

  • Product Hunt's own visual editor shows your launch page as you build it.

    #50 on Product Hunt

Show HN

5

HN front page

30
Show 22 more

YC Launches

20
Show 12 more

HF trending models

18
Show 10 more

HF trending spaces

17
Show 9 more

HF daily papers

20
Show 12 more

Lobsters

25
Show 17 more

Dev.to top

20
Show 12 more

Techmeme

15
Show 7 more

About this issue

366 items from 77 sources, 5 of them seen in several sources. 4 sources failed to fetch.

Source health

77
Which sources were fetched today, and how many items each returned.
SourceSectionItemsStatus
GitHub TrendingMain11Fetched
Product HuntMain50Fetched
Show HNMain5Fetched
HN front pageMain30Fetched
YC LaunchesMain20Fetched
HF trending modelsMain20Fetched
HF trending spacesMain20Fetched
HF daily papersMain20Fetched
LobstersMain25Fetched
Dev.to topMain20Fetched
TechmemeMain15Fetched
AndroidX releasesAndroid · Official & releases45Fetched
Android Developers BlogAndroid · Official & releases4Fetched
Android Studio releasesAndroid · Official & releases3Fetched
Kotlin blogAndroid · Official & releases3Fetched
Kotlin releasesAndroid · Official & releases0Failed
Compose Multiplatform releasesAndroid · Official & releases4Fetched
Android Developers YouTubeAndroid · Official & releases0Failed
Kotlin on YouTube (JetBrains)Android · Official & releases0Failed
Google Developers BlogAndroid · Official & releases1Fetched
AndroidX merged API changesAndroid · AOSP / AndroidX insider0Fetched
Dove Letter (skydoves)Android · Experts5Fetched
skydoves on MediumAndroid · Experts0Fetched
Jake WhartonAndroid · Experts0Fetched
Zac SweersAndroid · Experts0Fetched
Chris BanesAndroid · Experts3Fetched
Ryan HarterAndroid · Experts0Fetched
Talking KotlinAndroid · Experts0Fetched
Joe BirchAndroid · Experts2Fetched
CommonsWare (Mark Murphy)Android · Experts3Fetched
TechYourChance (Vasiliy Zukanov)Android · Experts1Fetched
Kt. Academy (Marcin Moskała)Android · Experts2Fetched
Touchlab (Kotlin Multiplatform)Android · Experts3Fetched
Landscapist releasesAndroid · Library releases0Fetched
Balloon releasesAndroid · Library releases0Fetched
Sandwich releasesAndroid · Library releases0Fetched
Cloudy releasesAndroid · Library releases0Fetched
Compose Stability Analyzer releasesAndroid · Library releases0Fetched
Haze releasesAndroid · Library releases0Fetched
Compose Unstyled releasesAndroid · Library releases1Fetched
Coil releasesAndroid · Library releases0Fetched
Circuit releasesAndroid · Library releases0Fetched
Metro releasesAndroid · Library releases0Fetched
Molecule releasesAndroid · Library releases0Fetched
Turbine releasesAndroid · Library releases0Fetched
Paparazzi releasesAndroid · Library releases0Fetched
SQLDelight releasesAndroid · Library releases0Fetched
OkHttp releasesAndroid · Library releases2Fetched
Retrofit releasesAndroid · Library releases0Fetched
LeakCanary releasesAndroid · Library releases0Fetched
Koin releasesAndroid · Library releases0Fetched
Dagger / Hilt releasesAndroid · Library releases0Fetched
KSP releasesAndroid · Library releases0Fetched
kotlinx.coroutines releasesAndroid · Library releases0Fetched
kotlinx.serialization releasesAndroid · Library releases1Fetched
Ktor releasesAndroid · Library releases0Fetched
Apollo Kotlin releasesAndroid · Library releases0Fetched
Kermit releasesAndroid · Library releases0Fetched
Store releasesAndroid · Library releases0Fetched
Decompose releasesAndroid · Library releases1Fetched
Orbit MVI releasesAndroid · Library releases0Fetched
Roborazzi releasesAndroid · Library releases1Fetched
detekt releasesAndroid · Library releases0Fetched
ktlint releasesAndroid · Library releases0Fetched
MockK releasesAndroid · Library releases0Fetched
Lottie releasesAndroid · Library releases0Fetched
Authority Insights (leaks & teardowns)Android · Leaks & ecosystem3Fetched
9to5Google · AndroidAndroid · Leaks & ecosystem8Fetched
Android AuthorityAndroid · Leaks & ecosystem4Fetched
Android FaithfulAndroid · Leaks & ecosystem1Fetched
Android WeeklyAndroid · Community15Fetched
GitHub Trending · KotlinAndroid · Community13Fetched
Lobsters · androidAndroid · Community1Fetched
HN · AndroidAndroid · Community11Fetched
ProAndroidDevAndroid · Community2Fetched
Kotlin WeeklyAndroid · Community1Fetched
Philipp Lackner (YouTube)Android · Community0Failed
1 of 5

Pick 1. DataStore 1.3.0 is stable with built-in encryption

Why it matters: If you encrypt tokens or settings by hand on top of DataStore, you can now use a first-party option instead.

Google released DataStore 1.3.0, the Jetpack library for storing settings and small data. A new artifact, datastore-tink, encrypts what you store using Google's Tink library. Kotlin Multiplatform apps get web storage backends. A new DataStore Builder replaces the old factory, the library now ships Baseline Profiles for faster startup, and a data-loss bug in the Guava variant is fixed.

1 of 4

Pick 1. VoiceStudio offers a fully local alternative to ElevenLabs

Why it matters: Voice work no longer has to mean sending recordings to a cloud vendor, which changes the cost and privacy math for voice features.

VoiceStudio is an open-source app that does voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation entirely on your own machine. It added about sixteen hundred stars on GitHub today and has around eighty-seven thousand in total. It positions itself directly as a local replacement for ElevenLabs, the popular paid voice service.