← The 5 stories that mattered

Everything collected ·

All 335 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. Google says detachable Googlebooks are the next form factor

    Why it matters: If your app may run on Googlebooks, plan layouts that work both with a keyboard and mouse and as a touch-only tablet.

    At Android Dev Summit earlier this week, Google said Googlebook detachables will be the next form factor, after clamshell laptops and convertibles. A detachable is usually a tablet whose keyboard comes off. 9to5Google reported the update and says they are coming soon. For app developers, it means one more device that switches between keyboard use and touch use.

  2. Pick 2. Mutation testing checks whether AI-written tests catch bugs

    Why it matters: As agents write more of your tests, mutation testing gives you a measure of how much those tests actually protect.

    Philipp Lackner, an Android educator on YouTube, walks through mutation testing. AI agents can generate many test cases quickly, but more tests do not mean better ones. Mutation testing makes small deliberate changes to your code and checks whether any test fails. If none does, those tests were not really checking that code.

  3. Pick 3. An open-source app runs Claude Code on an Android phone

    Why it matters: Phones are becoming a place to direct coding agents, not just to read their output.

    Mobile-Harness is an open-source Android app that puts a coding agent on your phone. You can chat with the agent, run Linux commands, edit files, review code changes and preview web apps on the device. It is trending in Kotlin on GitHub with close to 800 stars.

  4. Pick 4. CameraX prepares a low-light boost effect

    Why it matters: Camera apps may soon get brighter night previews from CameraX without writing their own image processing.

    Two changes merged into AndroidX, Google's Jetpack libraries, point to new CameraX work. One adds a state and an availability check for a low-light boost effect, which brightens dark scenes. The other adds a check that picks output sizes a camera effect can handle. Neither has shipped in a release yet.

  5. Pick 5. Android Auto video apps are still coming soon

    Why it matters: If you build media apps, do not plan an in-car video launch until Google publishes the details.

    In a brief update at its latest developer conference, Google said video and browser apps for Android Auto, its in-car display system, are still coming soon. 9to5Google notes that the deadline Google set for itself is close. Until then, car screens stay limited to audio, navigation and messaging style apps.

Also worth knowing

Releases, policy and leaks an Android engineer should know about this week.

Go deeper: every Android item, by lane

Official & releases

16
No new stable Jetpack library today: Studio Rabbit 2 stays the stable IDE pick, Compose Multiplatform 1.13.0 beta needs desktop libraries using experimental drag and drop to recompile, and the Appstate, Media3 1.12 and Test Core 1.8 alphas are for side branches.
Show 4 more

AOSP / AndroidX insider

2
Two CameraX changes point to a low-light boost delivered as a camera effect, with a check that picks output sizes the effect can handle.
  • Add CameraEffect resolution validator to prioritize sizes

    A validator that ranks output sizes for camera effects suggests CameraX is making effects safer to combine with any resolution, likely groundwork for the low-light boost effect merged alongside it.

  • Add LowLightBoostEffectState and availability

    A state and availability API points to low-light boost delivered as a CameraX effect, so apps can check support and show when it is active, possibly on devices without the hardware mode.

Experts

18
Watch Philipp Lackner on mutation testing to catch weak AI-written tests, and read Touchlab's two-part series on flaky coroutine and Turbine tests and Kt. Academy on Flow bugs that look correct.
Show 10 more

Library releases

11
kotlinx.serialization 1.12.0 and KSP 2.3.13 are the updates worth taking, Compose Unstyled 2.10.2 keeps focus inside dialogs and sheets, Metro 1.5.1, Ktor 3.6.1, Apollo 4.4.4, OkHttp 5.5.1 and Roborazzi 1.77.0 are safe patches, and Decompose 3.6.0 is still beta.
  • Patch Changes 649c471 : Make dialogs, modal bottom sheets, and modal drawers behave inside of a Host the same as without. Tab and Shift+Tab now stay inside the topmost modal, background controls receive no keystrokes, and closing the modal restores the previous focus. b59481b …

  • Fixes [IR/IC] Avoid recompiling unrelated files in the graph module when the constructor of an upstream @Contributes* class changes. [Gradle] Fix false hidden-dependency reports for contributions from associated compilations, such as main sources in tests. This particularly…

  • New [metrox-viewmodel-compose] Add support for linuxX64 . [FIR] Add the diagnostic-level compiler option to change the severity of Metro diagnostics reported in FIR. It works like kotlinc's -Xwarning-level but can also lower errors and use IDE-only levels. See changing…

  • Version 5.5.1

  • Version 4.12.1

  • What's Changed Add KSContextParameter and KSFunctionDeclaration.contextParameters to the API ( #3216 ) Improve diagnostics by returning last round dismissible errors when KSP fails ( #3196 ) Add opt-in processor classloader caching ( ksp.classloader.cache.processors=true ) to…

  • 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…

  • Published 29 October 2026 Improvements KTOR-10005 Native accepted TCP sockets do not enable TCP_NODELAY, unlike JVM KTOR-9966 Netty poor performance on delay calls KTOR-4206 The "com.typesafe.config.ConfigException$Missing" exception leaks from the typesafe config library when…

Show 3 more
  • A patch version to fix Java codegen generating bad code when using custom scalars mapped to Long or Float. 👷‍♂️ All changes [FIX] codegen: fix Java codegen generating bad code when using custom scalars mapped to Long or Float. ( #7032 )

  • 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

17
Google says detachable Googlebooks come after clamshells and convertibles, Android Auto video and browser apps are still coming soon, and Android 17 sits near 1 percent of devices.
Show 9 more

Community

39
This week's Android Weekly covers AppFunctions toggled at runtime, Kotlin 2.5 value classes and when KSP is the right tool, while GameNative and an app that runs Claude Code on an Android phone trend in Kotlin.
Show 31 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. HackerBooks lists the books Hacker News readers recommend

    Why it matters: Community archives are full of trusted recommendations, and an AI model can now turn them into a product quickly.

    A Show HN project collects about 16 and a half thousand books that at least two different Hacker News commenters mentioned. The author was inspired by HackerTube, a similar site for videos, and says Claude built it. It is the top Show HN post and second on the front page, with about a thousand points and nearly 200 comments.

  2. Pick 2. Local voice dictation apps climb on GitHub

    Why it matters: Speech models small enough for a laptop make paid cloud dictation easier to replace.

    Hex is an open-source voice dictation app that runs on your own computer, on Mac, Windows and Linux. It gained about 1,200 stars in a day on GitHub. Handy, another free speech-to-text app that works fully offline, is also trending, near 37 thousand stars.

  3. Pick 3. Click offers managed AI agents for any model

    Why it matters: Running agents safely is becoming a service you buy, separate from the model you choose.

    Click, the top launch on Product Hunt today, is a managed service for running AI agents that works with any model. On GitHub, CopilotKit's OpenBot gives each AI coworker its own computer, with a browser, files and tools, and records every action. Both treat where an agent runs as the product.

  4. Pick 4. OmniDiff, an open-source diff tool that understands content

    Why it matters: As agents produce more code changes, better tools for reading diffs matter as much as tools for writing code.

    OmniDiff is an open-source Git diff tool written in Rust. Its author studied real changes in open-source repositories to design it, and says it can compare code in 25 languages, config files and more. It reached the Hacker News front page and Show HN, with about 180 points.

Go deeper: themes, product notes, every source

Themes across sources

5
On-device AI · Coding-agent control surfaces · Agent sandboxes · Verifying agent work · Community-curated catalogs

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

On-device AI

Rising · 10 items from 7 sources

Hex, a local voice dictation app for Mac, Windows and Linux, added about 1,200 GitHub stars in a day, and Handy, a free offline speech-to-text app, is near 37 thousand. FreeToken pitches running very large models on a desktop, Product Hunt lists Fluent 2 with AI teammates that run locally on a Mac, Liquid AI's LFM3 small models keep trending on Hugging Face, and teardowns show an offline mode coming to Gemini Live.

Why now. Speech and language models small enough for a laptop or phone are now good enough for daily work, so privacy and no subscription become selling points.

anomalyco/hexGitHub Trending

Coding-agent control surfaces

Rising · 11 items from 4 sources

t3code added about 3,100 stars, the most on GitHub today. Product Hunt adds agentmash, open-source multiplayer AI for a team's coding agents, Termy, which puts a coding agent in the Mac notch, and Usage for Claude and ChatGPT, which shows plan limits on every Apple device. In Kotlin, Mobile-Harness runs Claude Code on an Android phone, and ProAndroidDev shows other models running inside Claude Code and Android Studio.

Why now. People run several agents a day across devices, so watching, sharing and budgeting them has become its own product category.

pingdotgg/t3codeGitHub Trending

Agent sandboxes

Rising · 6 items from 3 sources

CopilotKit's OpenBot gives each AI coworker its own computer with a browser, files and tools, and records every action. OpenMausBot ships a virtual machine for bots, Lightpanda's headless browser for agents keeps climbing, Click tops Product Hunt with a managed agents API for any model, and SpaceO gives agents their own Mac screen.

Why now. Agents now take real actions on computers, so giving them a separate, recorded place to work is safer than sharing the user's machine.

CopilotKit/OpenBotGitHub Trending

Verifying agent work

Rising · 8 items from 4 sources

Philipp Lackner argues for mutation testing to check whether AI-written tests catch anything, and ProAndroidDev asks who debugs agent-written Kotlin at 2 AM. Y Combinator's Hue, Composal and Mirrors test and correct agents, while Product Hunt lists telemetry.dev, Specsight and Faylee for watching and fixing what agents ship.

Why now. Agents now write both the code and its tests, so the old signal of a green test run says less than it used to.

Why You MUST Stick to Mutation Testing (Never Have Bad AI-Written Tests Anymore)Philipp Lackner (YouTube)

Community-curated catalogs

New · 2 items from 2 sources

HackerBooks, a list of about 16,500 books that at least two Hacker News commenters mentioned, is the top Show HN post with about 1,000 points. It was inspired by HackerTube, a video site built from Hacker News comments, which still leads the front page with about 2,300 points.

Why now. Models make it cheap to mine years of public comments for recommendations, and the author says Claude built HackerBooks.

Show HN: HackerBooks – HackerTube, but for books mentioned on HNShow HN

Fading: Open-weight frontier models (last seen 2026-11-01) · Anti-slop design skills (last seen 2026-11-01) · Chat share-link exploits (last seen 2026-11-01) · Agent memory layers (last seen 2026-10-31) · Agent supply-chain safety (last seen 2026-10-31) · World models (last seen 2026-10-31) · Agent-ready Android (last seen 2026-10-29) · Android XR glasses (last seen 2026-10-29) · Agents as security auditors (last seen 2026-10-26) · Open voice models (last seen 2026-10-26)

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

Show HN: HackerBooks – HackerTube, but for books mentioned on HN

productShow HN, HN front page1,002 pts · 191 comments

What
HackerBooks, a site listing about 16,500 books that at least two different Hacker News commenters mentioned, modeled on HackerTube. The author says Claude built it.
For whom
Hacker News readers looking for books the community actually recommends.
Problem
Good book recommendations are scattered across years of comment threads, and store rankings favor marketing.
Why now
AI models can extract and clean book mentions from a huge comment archive, and an agent can build the site around them.
Wedge
The two-commenter rule, a simple filter that keeps one-off mentions out.
Money
Side project; book links could carry affiliate income later.
Like
HackerTube · Goodreads · Hacker News Books · Five Books

LessonA clear inclusion rule makes a curated list trustworthy; say exactly why each item is there.

anomalyco/hex

repoGitHub Trending★ 1,179 today

What
Hex, a voice dictation app that runs locally on Mac, Windows and Linux.
For whom
People who type a lot, including developers prompting agents, and want dictation without sending audio away.
Problem
Built-in dictation is weak and good cloud dictation tools charge a subscription and process audio on their servers.
Why now
Open speech models now run fast enough on ordinary laptops.
Wedge
Local and cross-platform, one app for all three desktop systems.
Money
Not stated; open source today.
Like
Handy · Wispr Flow · Superwhisper · macOS Dictation

LessonWhen a paid category's core tech becomes free, a local, private version is the obvious wedge.

Click

productProduct Hunt#1 on Product Hunt

What
Click, a managed agents API that works with any model, the top Product Hunt launch today.
For whom
Developers building agents who do not want to run the loop, tools and state themselves.
Problem
Running agents in production means hosting long tasks, tool calls and memory, often tied to one model vendor.
Why now
Several model vendors now offer managed agents for their own models, leaving room for a neutral one.
Wedge
Model independence.
Money
Likely usage-based API pricing.
Like
Claude Managed Agents · OpenAI Agents SDK · Letta · Modal

LessonWhen each vendor builds the same layer for its own models, the neutral version has a ready pitch.

Show HN: OmniDiff – Opensource, super fast, content aware Git difftool, in Rust

productShow HN, HN front page176 pts · 43 comments

What
OmniDiff, an open-source, content-aware Git difftool written in Rust that diffs code in 25 languages, config files and more.
For whom
Developers who review many changes and find line-by-line diffs noisy.
Problem
Plain text diffs show moved code, reformatting and config changes as walls of red and green.
Why now
Coding agents produce more and larger changes, so reading diffs is a bigger share of a developer's day.
Wedge
Plugs into Git as a difftool, and the author designed it from real diffs in open-source repositories.
Money
Open source, no model yet.
Like
difftastic · delta · Beyond Compare · SemanticDiff

LessonStudy real usage data before designing a tool; it tells you which cases matter.

Show HN: Point your camera at a landscape to learn about its geology

discussionHN front page, HN · AndroidAndroid161 pts · 38 comments

What
An app that paints geologic maps over landscapes using augmented reality, so you can point your camera and identify the mapped rocks.
For whom
Hikers, travelers and students curious about the land around them.
Problem
Geologic maps exist but are hard to read and match to what you see in front of you.
Why now
Phone AR and location accuracy are good enough to align map data with a real view.
Wedge
Turning existing public map data into a camera overlay anyone can use.
Money
Not stated; a paid app or offline map packs are likely options.
Like
PeakFinder · Rockd · Google Lens · Flyover Country

LessonExpert data becomes a consumer product when you put it where people already look, through the camera.

techjarves/Mobile-Harness

repoGitHub Trending · KotlinAndroid★ 20 today

What
Mobile-Harness, an open-source Android app for chatting with a coding agent, running Linux commands, editing files, reviewing diffs and previewing web apps on the phone.
For whom
Developers who want to steer a coding agent away from their desk.
Problem
Agents run on laptops or servers, and checking or redirecting them from a phone means remote desktop or a chat bridge.
Why now
Agents work for long stretches on their own, so the human mostly reviews and redirects, which fits a phone.
Wedge
A full terminal, file editor and diff review in one Android app.
Money
Open source, no model yet.
Like
Termux · Claude mobile app · GitHub Mobile · Replit mobile

LessonWhen work becomes supervision, the device that wins is the one people always carry.

FlashML-org/FreeToken

repoGitHub Trending★ 242 todayHype flag

What
FreeToken, a tool that says it brings datacenter-scale model serving to the desktop so large models run locally and fast.
For whom
Developers and enthusiasts who want to run big open models on their own hardware.
Problem
Large open models need server GPUs, so most people rent them or use paid APIs.
Why now
Open models are good enough to want locally, and serving techniques from datacenters are now open source.
Wedge
Bringing server-grade serving tricks to a single machine.
Money
Open source, no model yet.
Like
llama.cpp · Ollama · LM Studio · vLLM

Datacenter-scale on a desktop is a broad claim; the brief has no benchmarks or hardware requirements.

LessonBorrowing a technique from big infrastructure and shrinking it is a clear story; back it with numbers.

CopilotKit/OpenBot

repoGitHub Trending★ 175 today

What
OpenBot by CopilotKit, open-source AI coworkers that each get their own computer with a browser, files and tools, where every action is decided before it happens and recorded after.
For whom
Teams that want agents doing real work but need a record of what they did.
Problem
Agents that use a person's own machine are hard to audit and risky to leave running.
Why now
Computer-use agents are capable enough to give real tasks, so isolation and audit trails are the blockers.
Wedge
A separate computer per agent plus a full action record, with any model.
Money
Open source; a hosted version is likely.
Like
OpenMausBot · Manus · SpaceO · E2B

LessonFor a tool people fear, lead with the safeguards; the audit trail is the product.

agentmash

productProduct Hunt#6 on Product Hunt

What
agentmash, open-source multiplayer AI for a team's coding agents.
For whom
Engineering teams where several people run coding agents on the same codebase.
Problem
Each developer's agent works alone, so teams duplicate work and miss each other's context.
Why now
Coding agents are standard on many teams, so coordination between them is the next friction.
Wedge
Open source and team-first rather than single-user.
Money
Open source; a hosted team plan is likely.
Like
MAO · Orkas · GitHub Copilot · Slack

LessonSingle-player tools grow into multiplayer ones; be early to the shared version.

Termy

productProduct Hunt#7 on Product Hunt

What
Termy, which puts your coding agent in the Mac notch.
For whom
Mac developers who run an agent in the background while doing other work.
Problem
Checking on an agent means switching to a terminal window and losing focus.
Why now
Agents run long enough on their own that a glanceable status beats a full window.
Wedge
Unused screen space that is always visible.
Money
Likely a paid Mac app.
Like
AC Bridge · NotchNook · Claude desktop app · Raycast

LessonPut the status of long-running work where the eye already goes.

Usage for Claude + ChatGPT 4.0

productProduct Hunt#3 on Product Hunt

What
Usage for Claude and ChatGPT 4.0, which shows Claude and ChatGPT plan limits on Mac, iPhone, iPad and Apple Watch.
For whom
Heavy users on subscription plans who keep hitting usage limits.
Problem
Limits reset on schedules that are hard to see, so people run out mid-task or waste quota.
Why now
Paid AI plans now meter usage in windows, and people pay for more than one.
Wedge
One glance across every Apple device, including the watch.
Money
Likely a paid app.
Like
ccusage · Coding Wrapped · iStat Menus

LessonEvery limit a platform imposes creates a small market for making it visible.

Riverside Agents

productProduct Hunt#4 on Product Hunt

What
Riverside Agents, a team of AI agents for video that produce, edit, clip and post.
For whom
Podcasters and creators already recording on Riverside.
Problem
Turning a recording into clips and posts takes hours of editing after the show.
Why now
Models can now follow a transcript, pick moments and cut video well enough to automate the routine parts.
Wedge
Agents attached to the place the recording already lives.
Money
Likely part of Riverside's paid plans.
Like
Descript · Opus Clip · CapCut · Screen Studio

LessonOwn the raw material, then add agents for every step after it.

beenuar/AiSOC

repoGitHub Trending★ 446 today

What
AiSOC, an open-source AI security operations center with alert fusion, LLM-agent triage, MITRE ATT&CK investigation and a replayable decision ledger for every agent step.
For whom
Security teams drowning in alerts, especially small teams without a full operations center.
Problem
Analysts triage thousands of alerts by hand, and commercial tools are expensive.
Why now
Agents can now read logs and follow investigation playbooks, and a decision record makes their calls reviewable.
Wedge
Open source plus a replayable ledger, so every agent decision can be checked.
Money
Open source, no model yet.
Like
Dropzone AI · Google SecOps · Splunk SOAR · Torq

LessonIn high-stakes work, showing how the AI reached a decision matters as much as the decision.

shiyu-coder/Kronos

repoGitHub Trending★ 630 todayHype flag

What
Kronos, a foundation model trained on the language of financial markets.
For whom
Quant researchers and fintech developers experimenting with market data.
Problem
General language models are not trained on price data, and custom market models are costly to build.
Why now
Foundation-model training recipes are public enough to apply to time series like candlestick data.
Wedge
An open model for a domain usually kept private.
Money
Open source research project.
Like
TimesFM · Chronos · BloombergGPT

Market prediction claims are easy to overstate; the brief shows no trading results.

LessonApplying a proven recipe to a new kind of data is a fast way to a new category.

utkarshdalal/GameNative

repoGitHub Trending · KotlinAndroid★ 32 today

What
GameNative, an open-source app for native PC gaming on Android with Steam, Epic, GOG and Amazon integrations.
For whom
Android handheld and phone owners who want to play their existing PC game libraries.
Problem
Running PC games on Android means juggling emulators, compatibility layers and store logins by hand.
Why now
Android handhelds and phone GPUs are powerful enough, and compatibility layers have matured.
Wedge
Store integrations, so your existing library shows up without manual setup.
Money
Open source, no model yet.
Like
Winlator · GameHub · Steam Link · DroidDeck

LessonImport what users already own; a library they paid for is the strongest reason to switch.

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

17
  • claude-mem adds about 1,500 stars and passes 109 thousand, as agent memory becomes its own layer.

    ★ 1,526 today

  • Lightpanda, a headless browser built for agents rather than people, adds about 800 stars.

    ★ 825 today

  • Kronos: A Foundation Model for the Language of Financial Markets

    ★ 630 today

  • t3code adds about 3,100 stars, the most on GitHub today.

    ★ 3,094 today

  • OpenMausBot, an open-source bot with its own virtual machine, adds about 900 stars.

    ★ 922 today

  • The long-running list of free public APIs, trending again near 495 thousand stars.

    ★ 324 today

  • Handy, a free, offline speech-to-text app, nears 37 thousand stars as local dictation trends.

    ★ 339 today

  • Turns Claude Code into a game studio with 49 agents and 72 skills arranged like a real studio hierarchy.

    ★ 967 today

Show 9 more
  • Kornia, a geometric computer vision library for spatial AI, back on the trending list.

    ★ 101 today

  • Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.

    ★ 446 today

  • An open-source Zi Wei Dou Shu astrology chart engine, still among the fastest risers.

    ★ 941 today

  • Local voice dictation for mac, windows and linux

    ★ 1,179 today

  • Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.

    ★ 175 today

  • LIST OF ALL MY JAILBREAKS

    ★ 726 today

  • A collection of tutorials on LLMs, RAG and agent apps adds about 1,200 stars.

    ★ 1,191 today

  • FreeToken claims datacenter-style model serving on a desktop.

    ★ 242 today

  • Hyprland, a tiling Wayland compositor for Linux, trending again.

    ★ 38 today

Product Hunt

50
  • Managed agents API that works with any model

    #1 on Product Hunt

  • Screen Studio 4.0 adds editing by transcript and a camera cutout to its screen recorder.

    #2 on Product Hunt

  • Claude + ChatGPT limits on your Mac, iPhone, iPad and Watch

    #3 on Product Hunt

  • A team of AI agents for video: produce, edit, clip, post

    #4 on Product Hunt

  • Mirror, copy or two-way sync folders on a Mac.

    #5 on Product Hunt

  • open-source multiplayer AI for teams' coding agents

    #6 on Product Hunt

  • Your coding agent, in the notch

    #7 on Product Hunt

  • Embage lets companies build agents for their customers and analyze the workflows they run.

    #8 on Product Hunt

Show 42 more
  • An AI research agent that comes with its own cloud lab.

    #9 on Product Hunt

  • BeeBranch, a local-first desktop Git client.

    #10 on Product Hunt

  • A tiny 3D hamster that lives on your desktop.

    #11 on Product Hunt

  • Fluent 2 runs AI teammates locally on a Mac rather than in the cloud.

    #12 on Product Hunt

  • Ideogram's Precise Edit changes parts of an image using a context window.

    #13 on Product Hunt

  • A game about building a medieval abbey from 1258 to today.

    #14 on Product Hunt

  • Follow AI models and agents the way you follow people.

    #15 on Product Hunt

  • One dashboard for revenue, analytics and site performance.

    #16 on Product Hunt

  • erndnew

    ernd, a credit card for AI spending with faster inference access and cash back, on Product Hunt and YC.

    #17 on Product Hunt

  • Everything you saved across apps in one visual library.

    #18 on Product Hunt

  • Skips or mutes scenes you mark while watching Netflix.

    #19 on Product Hunt

  • A screen-light makeup mirror for iPhone.

    #20 on Product Hunt

  • A Wrapped-style recap of how you use Claude Code and Codex.

    #21 on Product Hunt

  • telemetry.dev offers observability for AI agents.

    #22 on Product Hunt

  • Brings back a Launchpad-style app grid on macOS 26.

    #23 on Product Hunt

  • Specsight tracks product behavior for teams shipping fast with AI.

    #24 on Product Hunt

  • A character on your Mac that claims to handle 232 tasks.

    #25 on Product Hunt

  • An AI workspace in your browser's new tab.

    #26 on Product Hunt

  • GitHub Copilot Fusion picks and combines models for each coding task.

    #27 on Product Hunt

  • Write a TypeScript function and get an admin screen for it.

    #28 on Product Hunt

  • Smart lights that show when Claude Code or Codex needs your attention.

    #29 on Product Hunt

  • Cleans documents for AI use and shows what was removed.

    #30 on Product Hunt

  • Turns competitor ad insights into app install campaigns.

    #31 on Product Hunt

  • Backenly pitches a backend that coding agents can run on their own.

    #32 on Product Hunt

  • An SSH client with a built-in agent and a desktop per server.

    #33 on Product Hunt

  • Godwit, an open-source, AI-native email client.

    #34 on Product Hunt

  • Design a database schema on a canvas and get the SQL written for you.

    #35 on Product Hunt

  • SpaceO gives AI agents their own screen on your Mac so they do not take over yours.

    #36 on Product Hunt

  • SKI, a voice-first coding harness.

    #37 on Product Hunt

  • Hides Mac menu bar clutter and pins single actions.

    #38 on Product Hunt

  • Lets your family get your passwords if something happens to you.

    #39 on Product Hunt

  • Tap your Mac's palm rest to trigger actions.

    #40 on Product Hunt

  • Shows flight prices in loyalty points directly on Google Flights.

    #41 on Product Hunt

  • Shows your desktop in 3D on a Quest headset.

    #42 on Product Hunt

  • Deploy vibe-coded apps on your own server instead of a hosted platform.

    #43 on Product Hunt

  • Point at your running app and your agent changes the matching code.

    #44 on Product Hunt

  • Faylee turns a bug report into one link a coding agent can fix from.

    #45 on Product Hunt

  • Extracts key details from any webpage or PDF.

    #46 on Product Hunt

  • Teable's no-code database builder comes to phones.

    #47 on Product Hunt

  • fastbrowse claims to be the fastest open-source browser agent.

    #48 on Product Hunt

  • Canva Brush, a vision-language model that edits your existing designs.

    #49 on Product Hunt

  • Answers questions during a call on a Mac, not after it.

    #50 on Product Hunt

Show HN

4

HN front page

30
Show 22 more

YC Launches

20
Show 12 more

HF trending models

19
Show 11 more

HF trending spaces

18
Show 10 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

335 items from 77 sources, 10 of them seen in several sources. 2 sources failed to fetch.

Source health

77
Which sources were fetched today, and how many items each returned.
SourceSectionItemsStatus
GitHub TrendingMain17Fetched
Product HuntMain50Fetched
Show HNMain4Fetched
HN front pageMain30Fetched
YC LaunchesMain20Fetched
HF trending modelsMain20Fetched
HF trending spacesMain20Fetched
HF daily papersMain20Fetched
LobstersMain25Fetched
Dev.to topMain20Fetched
TechmemeMain15Fetched
AndroidX releasesAndroid · Official & releases13Fetched
Android Developers BlogAndroid · Official & releases4Fetched
Android Studio releasesAndroid · Official & releases5Fetched
Kotlin blogAndroid · Official & releases1Fetched
Kotlin releasesAndroid · Official & releases0Fetched
Compose Multiplatform releasesAndroid · Official & releases1Fetched
Android Developers YouTubeAndroid · Official & releases0Failed
Kotlin on YouTube (JetBrains)Android · Official & releases0Failed
Google Developers BlogAndroid · Official & releases1Fetched
AndroidX merged API changesAndroid · AOSP / AndroidX insider2Fetched
Dove Letter (skydoves)Android · Experts5Fetched
skydoves on MediumAndroid · Experts0Fetched
Jake WhartonAndroid · Experts0Fetched
Zac SweersAndroid · Experts0Fetched
Chris BanesAndroid · Experts2Fetched
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 releases2Fetched
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 releases1Fetched
kotlinx.coroutines releasesAndroid · Library releases0Fetched
kotlinx.serialization releasesAndroid · Library releases1Fetched
Ktor releasesAndroid · Library releases1Fetched
Apollo Kotlin releasesAndroid · Library releases1Fetched
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 & ecosystem4Fetched
9to5Google · AndroidAndroid · Leaks & ecosystem7Fetched
Android AuthorityAndroid · Leaks & ecosystem6Fetched
Android FaithfulAndroid · Leaks & ecosystem1Fetched
Android WeeklyAndroid · Community15Fetched
GitHub Trending · KotlinAndroid · Community16Fetched
Lobsters · androidAndroid · Community1Fetched
HN · AndroidAndroid · Community4Fetched
ProAndroidDevAndroid · Community3Fetched
Kotlin WeeklyAndroid · Community1Fetched
Philipp Lackner (YouTube)Android · Community2Fetched
1 of 5

Pick 1. Google says detachable Googlebooks are the next form factor

Why it matters: If your app may run on Googlebooks, plan layouts that work both with a keyboard and mouse and as a touch-only tablet.

At Android Dev Summit earlier this week, Google said Googlebook detachables will be the next form factor, after clamshell laptops and convertibles. A detachable is usually a tablet whose keyboard comes off. 9to5Google reported the update and says they are coming soon. For app developers, it means one more device that switches between keyboard use and touch use.

1 of 4

Pick 1. HackerBooks lists the books Hacker News readers recommend

Why it matters: Community archives are full of trusted recommendations, and an AI model can now turn them into a product quickly.

A Show HN project collects about 16 and a half thousand books that at least two different Hacker News commenters mentioned. The author was inspired by HackerTube, a similar site for videos, and says Claude built it. It is the top Show HN post and second on the front page, with about a thousand points and nearly 200 comments.