PH热榜 | 2026-06-14

the connects to email, calendar, CRM, and meeting notes all at once is the setup that determines whether this becomes infrastructure you depend on or a tool you trial and abandon. each integration is a potential point of failure and the value compounds only when all of them are working. what does onboarding actually look like and how long before the cross-context awareness starts producing useful outputs rather than just having access to the data

Kudos for making this serious, full-stack email client instead of just a wrapper plugin. Quick question. If run two different businesses from two different accounts, does Slashy keep the context and brand voices completely separate? @harsha_gaddipati

been using it for 3months now, the email search is really good. i’m waiting for some upcoming updates where my agents can also use Slashy, that’d be pretty sick. are you folks working on that?

By far one of the best productivity tools out there!!! Completely changed how I view email and how I manage my time. The texting agent is incredibly helpful in between meetings and when youre on the go. lets gooooo slashy team!!!

Slashy is great! I use it for everything

As a student, I receive a lot of emails from teachers, clubs, and projects. Slashy looks like a great way to save time and keep my inbox organized. The AI-powered reply feature seems especially useful for busy students. Congrats on the launch and good luck!

slashy has been great for my founder inbox. huge congrats on the launch!

Building a full client instead of bolting onto Gmail is the part most people won't touch, I guess the switching cost scares everyone into shipping another wrapper! So the voice memory has to carry real weight to justify the move, and it reads like you know that. Congrats on the launch.

Wow, this is amazing. Does it work with Gmail and other mail clients?

What specifically does Slashy do that existing tools like Superhuman, Fyxer, Gmail AI, Outlook Copilot, and others cannot?

This looks very useful, looks like a lot of the tedious work that I deal with in emails will be solved by this. Probably will be using the priority feature heavily, as it's becoming hard to find which emails need my attention now

Happy user here, great product from a great team. The sippet insert feature is killer!

Slashy is great — making it possible to avoid thinking about the minutiae of sending emails. Only feedback is more integrations or background work that leverage available context (eg auto drafts using notes from Granola meeting)

Been using it for the last few months and honestly love it, especially the iMessage integration! One of the smoothest experiences I’ve had getting used to a new product.

Been using for over a month now. It’s saved so many hours for me plus my emails are now very personalized.

How do you stop Slashy from texting you every single email? Is there some way to filter out only important emails?

I've been following slashy for a while super excited to see what you guys shipped today!

Congrats on the launch @harsha_gaddipati

Been using it every day. Especially enjoying the slashy text chat.

Phenomenal humans and phenomenal product.

Firing off emails from iMessage while on the go is genuinely something I never knew I needed until just now. The voice-matching piece is what separates useful AI email from the stuff that sounds like a robot wrote it.

top tier product, top tier team

Awesome product! My cofounder and I use it a lot.

best sales team in the world, always on and the tool is actually better than superhuman no joke. if there is an issue - you ping them and they fix it.

i can attest that slashy is excellent

The "no memory, no context" diagnosis is spot on - it's why most AI email tools feel like a stranger writing on your behalf. The interesting bet here is the assistant noticing the follow-up you forgot; drafting is solved, triage and memory are where the real value is. One question: how do you handle the trust line on actually sending? For me the scary part of email automation isn't the draft, it's the irreversible click. Does Slashy ever send on its own or always hand you the wheel?

The "why" behind design decisions is exactly what's missing when you hand off to AI agents. Tried it on a few sites and the output is way more useful than just extracting colors and fonts. Nice work, upvoted!

Love this! Which coding tool integration with Taste Lab do you recommend the most? Which one do you enjoy using?

This hits a real pain — telling an AI agent to build "in the style of X" almost always loses the spacing and type scale. Capturing the reasoning behind each design decision, not just the raw tokens, is the clever part. Does it export to a Tailwind config / design tokens I can drop straight into a build? Congrats on the launch!

Websites are becoming increasingly animated, how does it captuer animations styles? and unconventional animations?

Love the concept. Have you experimented with analyzing entire product ecosystems rather than individual pages? I'd be curious to see how Taste Lab handles consistency across marketing sites, product dashboards, and mobile experiences. 🤔

I like that Taste Lab explains the reasoning behind visual choices, not just colors and fonts. For AI-built frontends, that context could help avoid generic-looking pages. Would be interesting to see how it handles sites with several design systems.

The part I'd try first is running this on a messy personal portfolio, then using the breakdown as a prompt for a redesign instead of starting from a blank style guide. I like that it tries to explain why the spacing and type choices work, not just list tokens. Does Taste Lab keep a reusable brief/history for a site, or is each scan meant to be a fresh one-off export?

Had a friend who put me on to taste lab to extract specific components and it was super helpful, thanks for the software going to be putting my boys into it that are in the space for sure.

Very cool! Does it provide md files?

Very interesting product

Nice. Does it save the templates for the future designs?

@sunlinsen Congratulations, I like that this focuses on the reasoning behind the design, not just extracting colors and fonts. For AI-built interfaces, understanding why a layout works is much more useful than copying surface-level style tokens.

Congrats on the launch. The idea of extracting a website’s design DNA is interesting, especially for people trying to improve their landing pages.

Are you mostly targeting designers right now, or founders who want to improve their own product pages?

very cool idea! does it capture interaction and motion too (transitions, easing), or is it focused on the static layer for now?

Not only the idea, but also your landing page is nailed! Good job!

I’ve used @Permute forever (I hunted Permute 3.0 seven years ago!!), so I was nervous but hopeful about @charlie_monroe's promise that “everything changed but you’ll still feel at home”.

After beta testing it for a while leading up to launch, I can confirm that he was right.

This isn’t a shiny-new-app launch so much as a deep refactor of a Mac workhorse: rewritten UI using Apple’s newer frameworks, better presets for modern hardware, cleaner cropping, stronger metadata handling, and Workshop folded back into the main window as file actions.

Also: RIP DVD authoring. 📀😅

I don't even remember the last Mac I bought with an optical disk drive — which is why I'm glad that Charlie's still maintaining this app — now there's less tech debt, fewer weird legacy branches, and a much more comfortable home for the stuff people actually use Permute for now.

the preset layer is the part i'd sweat most — abstracting formats is easy, but hiding whether a job hits videotoolbox or falls back to software is where the speed/quality surprises come from.

@charlie_monroe Thanks for sharing your work!

The @Permute tool will be useful on my design projects. Will it be able to handle conversion to and from SVG format vector graphics?

Have never had one clean tool for all my media conversions on Mac, usually I juggle three. A full rebuild that still feels at home is the hard kind to pull off, nice work. For batch jobs, can you save a conversion preset and just drop files onto it later, or do you set it up fresh each time?

👋 Hey, Product Hunt, long time no see!

We first launched Athenic in 2023, and a lot has changed since.

Most "chat with your data" tools (Athenic 1.0 included) stop at an answer. Athenic 2.0 keeps going: it builds the dashboard, writes the report, and re-runs analyses on schedule — ask once, not every Monday.

Here's what's new:

• Automations — recurring analyses delivered to your inbox

• Business apps — connect your CRM, ERP, paid media channels & more, not just SQL databases

• Agentic Web research — Athenic monitors your competitors and surfaces market trends on its own

• Improved Charting — build full dashboards though chat, with more chart types and customizations
  

New usage-based pricing too, pay only for what you use. 2,000 free credits to start, no credit card required.

Happy to answer any questions and always grateful for feedback. What's the first thing you'd put on autopilot? 👇

— Jared

@eggro @jared_zhao The “analyze on autopilot” angle is strong if it helps teams move from dashboards to decisions. A lot of analytics tools show what happened, but the real value is surfacing what changed, why it matters, and what someone should look at next.

The part I find most interesting is trusting an agent to pick the join paths across tables on its own — that's usually where text-to-SQL tools quietly get the number wrong but still return something confident-looking. How are you handling the cases where the schema is ambiguous: does Athenic show its reasoning / the SQL it ran so an analyst can sanity-check, or is it more of a trust-the-answer flow?

the agentic data analyst framing implies the agent takes initiative rather than just responding. curious what the actual agent behavior looks like in practice. does it proactively flag anomalies in connected data, suggest analyses you haven't asked for, or is the agent label more about multi-step reasoning within a query than about autonomous action between sessions. the distinction matters a lot for how people would integrate this into their workflows

Hi PH 👋, I'm one of the makers of Cloudback. Today I'm bringing our Linear backup support to PH, because Linear is now where a lot of teams keep their full product context - issues, project decisions, cycle history, planning docs. Losing that overnight is a real risk, and Linear's native export only covers the issues table.

Here's what Cloudback does for a Linear workspace:

- Captures 23 data categories per workspace, including issues, projects, cycles, documents, custom views, initiatives, templates, comments, attachments, embedded files, workflow states, labels, teams, members, and the workspace structure itself.
- Restores the full workspace, not just a data dump - issues, projects, comments, and the structure all come back in the right order.
- Snapshot-based backup. Pick any backup, point it at an empty Linear workspace, confirm.

👥 Who it is built for:
- Engineering and product teams running their whole roadmap in Linear.
- Security and compliance teams that need backup evidence for SOC 2 audits.
- Founders who'd lose months of context if a workspace got wiped.

🔒 Security:
- AES-256 archives, customer-managed encryption keys via RSA Lockbox.
- SOC 2 Type II compliant.
- Cloudback Managed Storage in five regions, or bring your own storage across Amazon S3, Azure Blob, Google Cloud, OneDrive, Wasabi, Alibaba OSS, and OpenStack Swift.
- Audit log, Vanta integration, and many more.

Every plan starts with a free trial, so you can run a full backup and a restore drill before paying anything.

💬 Happy to answer any questions!

I like the focus on recovery, not just backup. Most teams only think about repo protection after something goes wrong, so having automated snapshots and a fast restore path gives a lot more peace of mind.

The restore-in-dependency-order detail is useful. Linear holds roadmap context beyond issues, so a dry-run restore before paying is a smart trust step. Can teams preview how projects, cycles, docs, and comments map before restoring into a new workspace?

Backup-and-restore is one of those things nobody values until the day they desperately do, which is exactly why it's a hard sell and an easy thing to under-price. The critique above about pricing clarity is the real one.

From a product-team angle: the question I'd want answered on the page isn't "do you back up Linear," it's "how fast and how granular is restore." If someone fat-fingers a bulk archive, can I recover one project to a point in time, or is it all-or-nothing? Recovery granularity is the actual product, the backup is just the prerequisite. Worth leading with that, because it's also what justifies the price.

the multi-platform support across ChatGPT, Claude, Gemini, and Grok is the right coverage but the capture mechanism for each is probably different. some of these have APIs, some require browser extension scraping, and the reliability and permissions vary a lot between them. curious how the actual capture works across platforms and whether there are any that work more reliably than others or require different setup steps

The user-curated memory choice makes sense for launch and support workflows where only a few AI conversations are worth keeping as project history. The first thing I would test is whether a teammate can save a Claude/ChatGPT thread, search it later, and prove it stayed private without turning it into another shared knowledge base. Does Memoriq support any team handoff model yet, or is the intended boundary strictly one private vault per person?

The capture asymmetry between platforms is the interesting engineering constraint here. ChatGPT via API is reliable, but Claude, Gemini, and Grok depend on DOM extraction. Meaning a UI change on any of those platforms can silently break capture or produce malformed saves.

How do you handle version drift detection? Is it a user-visible failure (capture stops until an extension update ships) or does Memoriq degrade gracefully and capture partial content? Claude in particular has changed its conversation UI structure multiple times this year. What does the extension update cadence look like when a platform breaks?

End-to-end encrypted + self-hostable is the combo that makes this trustworthy for anything work-related. The moment your AI history sits in someone else's plaintext cloud, you can't put real client or business context in it. Open source seals the deal because "private" only means something when you can verify it. The capture across four assistants is the hard part though - they don't all expose the same hooks. Curious how you handle that without it breaking every time one of them changes their UI.

I bounce between Claude and ChatGPT depending on the task and re-explaining my project context every time gets old fast. A shared memory layer makes sense in theory, but I'd want to know how it decides what's worth remembering vs noise. Is that automatic or do you curate it yourself?

Congrats on the launch! The E2E encryption and self-hosting options are a huge win for anyone worried about data privacy with LLMs. What cryptographic primitives are you using to handle the end-to-end encryption without bottlenecking the search/retrieval speed?

Ok but what can I do with stored conversations? Can I search across all my saved chats? Can I use them in other LLMs?

Hey Product Hunt 👋 I'm Randy.

I use Claude Code all day, and I kept losing track of what it was actually doing. It'd go heads-down for two minutes firing tools and burning context, and the terminal showed me everything except what I cared about. Which tools did it just run? How full is the context window?

I ended up with a usage CLI in one tab, a cost tool in another, and a statusline I had to squint at. I didn't want three side-tools. I wanted one surface to glance at. A cockpit.

So I built Conan, a native macOS app that sits beside Claude Code and turns its live session into a HUD:

- a streaming timeline of every prompt, tool call, and skill as it fires
- a context-window gauge you watch fill
- a usage and cost pulse

It reads Claude Code's local data. No telemetry, nothing about your code or prompts ever leaves the machine.

It's free to use. A one-time $29 unlocks Premium, no subscription, lifetime 1.x updates. macOS-first today; Windows and Linux folks can grab the waitlist.

I'd love your honest feedback, especially from people who live in Claude Code. What would make this a daily driver for you?

Try it → https://www.conan.sh

The local-only angle is important here; for a Claude Code HUD, I’d care less about another dashboard and more about making pauses, tool failures, and context pressure obvious at a glance.

@randydigital I understand the problem, but I keep wondering how many developers actually care about the mechanics versus the result.

If Claude spends 20 tool calls and 50k tokens but still produces the correct outcome, does the average developer want to inspect the journey? Or is this aimed more at engineering managers and power users who need visibility into cost and behavior?

Feels like there are potentially two very different customers hiding behind the same product.

@randydigital Interesting idea. One thing I’ve noticed with Claude Code is that the more information you expose, the more cognitive load you can accidentally create. At what point does the HUD become another dashboard people monitor instead of something that helps them stay focused?

I’m also curious whether users actually change their behavior after seeing token usage, tool calls, and context consumption in real time, or if it’s mostly reassurance that the agent is doing what they expect. Have you seen any surprising patterns there?

I live in the Claude Code terminal all day and honestly the bare CLI experience is fine until you're juggling more than one session — then it's just tabs everywhere and losing track of what's running where. A proper native Mac UI for this seems overdue. Does it let you switch between multiple active sessions easily, or is it more of a single-session viewer?

the interesting fork for a claude code cockpit is where you tap state — parsing the .claude jsonl logs vs wrapping the process for live events. the log route is robust but always a step behind.

Cool tool, the most pain point for me is skill usage, I don't know which skill claude code actual choose in conversation unless I specify to model.

Congrats on putting this together.

The problem is real IMO, especially when managing multiple concurrent agents. But to extend your analogy: if a cockpit has too many flashing lights and live streams, the pilot still gets overwhelmed.

For me, the ultimate HUD wouldn't just stream the raw data—it would summarize it. I’d love a feature inspired by how Gemini handles meetings: if I'm deeply focused on another task for 5 minutes and glance back, give me a quick "catch up" summary of what the agent actually achieved over those 5 minutes.

Distilling the chaos into a quick TL;DR status report.

As someone who lives in Claude Code and Cursor daily, a native Mac cockpit is exactly what I've been missing — losing track of context across terminal tabs is the real pain. Does it handle multiple parallel Claude Code sessions/worktrees in one view? Congrats on the launch!

The context-window gauge is the feature I didn't know I needed. I run long Claude Code sessions and the moment it starts compacting is exactly when things get fuzzy - having that fill level in sight beats finding out the hard way. The three-side-tools-into-one-cockpit framing is the right call too; I was squinting at a statusline for the same info. And keeping it all local (reads Claude Code's own data, nothing leaves the machine) is the detail that makes it actually usable for client work. How live is the timeline - true streaming as tools fire, or polled?

Putting it in Apple Wallet looks the right call, nobody's opening an app while the waiter stands there. Do the cards show which translations are machine-done vs native-verified yet?

Good job! I like the idea, specially given this can be a disaster when you're travelling with a kid.
Although I'm not sure if I want a seperate mobile application on my phone specifically for this.

The Apple Music-only limitation is a real constraint but I get why, keeping it focused probably helped ship this. Spotify support would be huge though. The idea of tying songs to places and moods instead of just playlists is something I didn't know I needed. Good luck with the launch!

Love how quiet and personal this is. Private, offline-first, songs pinned to places and moods, it feels much closer to a memory journal than another music app, and that's exactly the good part. I'm building in the private-memories space myself, so the "personal atlas of the songs you were" framing really lands for me.

One honest wish: Apple Music only is a tough gate. I'm not on it, so I can't actually try it, and I suspect a lot of people are in the same spot. Spotify support down the line would open this up to the audience the idea deserves. Rooting for it :)

I like the quiet, offline-first approach here. A music diary should feel personal instead of social by default, and tying songs to places and moods makes the listening history much more meaningful.

I like how personal this idea is. Music is often tied to places and moments, so being able to pin songs to a private map makes it feel more like a memory journal than just another music app.

The retro radar aesthetic is a perfect fit for this. Way more fun than a boring list of flights.

Love this. As a pilot, history buff, and aviation geek, I totally nerd out on this kind of stuff. Very cool UX.

The LabelLens product seems useful for many different types of people in lots of situations. However, @raizen_dev , I noticed that your description makes no mention of allergies or related categories. For example, I think this would be especially helpful for people with certain types of sensitivities to know whether a product was made in a facility where un-listed ingredients were used that may have come into contact with the product.

Transparency on food labeling is an important issue to tackle. Thanks for sharing your work!

Looks good, I would certainly try this, I like the scoring factor

Mad respect for shipping five products to get to this insight. The best tools always come from founder frustration. If I import a design I love as inspiration, how heavily does the AI rely on its layout versus its aesthetic style?

As a UI/UX designer I'm skeptical of most AI design tools but the "whole product" framing is interesting. Most just generate individual screens with no visual consistency. Does it maintain design language across different screen types?

Hey Product Hunt 👋 Suryansh here founder of 1Click Report — and yes, some of you saw us launch before, as an AI dashboard builder.

Over the last 6 months we have listened to our users and built capability where the entire marketing and analytics can be now run using Claude or any of your favorite AI models.

We ourselves run an AI marketing agency and this platform has helped us to scale from 5 clients to 30+ clients with just 3 people team as the entire clients marketing is now run by agents built using 1click report MCP.

Few of the things you can do using the MCP are -

• Ask anything in plain English. "Where am I wasting spend this week?" gets you one answer across Google Ads, Meta, GA4, Search Console and Stripe at once — instead of opening five tabs.

• Launch and manage campaigns. Create and adjust Google and Meta campaigns, keywords, budgets and audiences right from chat. Every write is paused by default — you approve before anything goes live.

• Audit and find waste. Point it at any account and it flags fatigued creative, broken tracking and runaway CPAs in minutes.

• Fix your funnel. Analyze your GA4 conversion funnels and see exactly where users drop off, then ask why.

• Stay on top of SEO and AEO. Pull Search Console data to see which queries are winning, which are slipping, and where the CTR opportunity is and automate SEO/AEO optimization

• Research and plan. Keyword volumes, competition and CPCs, then draft new ad groups.

• Set up 24/7 monitoring agents. "Alert me if CPA goes over $50" — it watches your accounts and emails you before it becomes Friday's surprise.

• Still build dashboards. The thing we first launched with is still here — just one feature now, not the whole product.

Because it's all MCP, you can wire these tools into your own agents — exactly how our 3-person team runs 30+ clients.

It works in Claude (Code, Desktop, web) and any MCP client. 7-day free trial, no card — PH folks get 30 days with code HUNT.

One thing I'd genuinely love your take on: what should we connect next — Klaviyo, LinkedIn Ads, or TikTok Ads?

Around all day — ask me anything.

I started out using 1ClickReport mostly for data analytics. The thing is, I wasn't really well-versed in how performance marketing actually works; the execution side of it always felt a bit out of reach. So at some point, I thought: why not use the real client data I already have in here to teach myself? Instead of doing a course, I'd just ask questions about our actual numbers and work through the concepts on real data until they properly clicked.

Honestly, it's been a better way to learn the subject than anything traditional I've tried.

This cool product helped me find my website weeknesses and increased my traffic

Hey Product Hunt 👋

I'm George, and DualChess is my solo project.

I love chess, but I always felt bad watching friends bounce off it. When there's a skill gap, the weaker player just loses every single game, and it stops being fun. I wanted a version where one moment of focus or quick reflexes could swing things, so a beginner always has a fighting chance against a stronger player or the AI.

So in DualChess the board is real chess, but you don't simply *take* a piece. Every capture kicks off a fast mini-game, and you have to win it to claim the piece. Six so far: Pong, Labyrinth, Quick Draw, Memory Match, Target Practice and Tug of War. Suddenly a losing position can be rescued by nerve, and a winning one can slip away if you choke under pressure.

I've also baked in a few special rule twists that quietly tilt the board toward the underdog. I'll let you discover those as you play. 😉

It started as a tiny "vs computer" prototype and grew into real-time online multiplayer, 4 AI difficulty levels, a global leaderboard, and a full installable PWA, all running in the browser with no download.

It's free to play. 🎁 Just for launch day today, the first 100 players get 1 day of Premium free with code BETA100. Grab it while it's live.

I'd genuinely love your feedback: does the twist make chess more fun, or just delightfully chaotic? And what mini-game should I add next? 😄

Thanks for checking it out!

Hi Product Hunt — I'm Ivan, the maker of Hive.

Hive is an open-source agent harness that drives SOTA coding agents (Claude, Codex, Pi) from a rough idea to a merge-ready PR. The mental model, borrowed from Kieran Klaassen's "the folder is the agent," is that every task is a directory: the folder's location is its state, and the .md files inside are the work. A daemon moves a task through 'brainstorm → plan → code → multi-agent review → PR', and you only step in when an agent actually needs you — usually just answering the brainstorm questions in your own editor (vim, in my case).

I've been dogfooding it hard. Hive's own codebase — now 55k+ lines of Ruby, not counting tests — was mostly written by Hive itself (about 70% when I last measured), and the demo above is a real run on a fresh project that ended in this merged PR: https://github.com/ivankuznetsov....

The recently shipped Hive v0.2.0 added a repo patrol that opens PRs on its own, a babysitter daemon that keeps open PRs rebased and green, and Telegram idea capture with voice notes.

You don't even have to leave your agent: Hive ships an OpenClaw skill (`openclaw skills install hive-cli` gives you a `/hive` command with guided setup), and you can drive it from inside the Hermes agent the same way.

Honest caveats up front:

- Hive is token-heavy by default (many subagents + multiple coding agents). It's free and open source, but to really try it I'd recommend a Claude Max + ChatGPT Pro (Codex) subscription — that's where it shines.
- Claude's tmux mode (the default — it bills against your Claude subscription instead of API credits) is the newest part of the stack — expect some rough edges.
- I'm a solo dev building this in spare time, so testing across OSes and workflows is thin. Feedback and issues are very welcome.
- Prefer a browser? Hivebox — a dockerized Hive with a web UI — is the next release, about a two weeks out. The Discord hears about it first.

Full write-up with the same demo: https://ikuznetsov.com/posts/int...
Discord: https://discord.gg/Qg5E7rMt
Repo: https://github.com/ivankuznetsov...

Happy to answer anything in the thread today

Interesting positioning. A lot of developers are comfortable delegating coding tasks to agents, but not necessarily the coordination layer around them.

How do you handle conflicting outputs from multiple agents? Is Hive choosing the "best" solution automatically, or does it surface tradeoffs for the developer to decide?

https://www.linkedin.com/pulse/sloptimization-ai-citation-rot-tools-fight-back-zohar-babin-xcahc

This article gives more background to the story of why this MCP exists with some real world examples.

Quality search is still a real problem with all the various AI assistants out there. This MCP has been in live real use by many people across different roles (legal, finance, academic, developers, product management, and every day use) for few months now, and I’ve been building and extending it per real world use-cases and needs. Feel free to try and share 🙏

This is a fun hook. Curious though, do you think the “roast” actually helps users improve their resume, or is it more purely entertainment/shareable content?