PH热榜 | 2026-01-22

Hi ProductHunt! 👋

I’m Steven Cen, the maker behind ChartGen AI.

Some of you might remember our previous launch, @Ada.im, which hit #1 Product of the Day and Week last September. While analyzing thousands of real users' feedbacks from that tool, we stumbled upon a fascinating pattern: non-technical users weren't just asking for text answers—they were desperate to see their data visualized.

As marketers, we all know the struggle: juggling CSVs from Facebook Ads, Google Analytics, Shopify, and TikTok, trying to piece together where our money is actually going. By the time we build the dashboard, the trend is already over. 🐢

That’s why we built ChartGen AI. We wanted to turn that "turtle-speed" manual reporting into an "owl-eyed" instant insight engine.

For all the online marketers here, this is specifically for you:

• Unified Data View: Drag & drop your ad spend data from any channel.

• Visualize the Journey: See exactly how every ad dollar converts across 30+ chart types tailored for marketing insights.

• Actionable Insights: Don’t just look at numbers; understand which campaign needs more budget and which one to kill—in seconds, not hours.

We believe data should tell a story, not a headache. I’d love to hear your feedback on our visualization templates!

We are live and eager to hear what you think. Drop a comment below with your thoughts or questions! 🚀

The follow-up questions ChartGen generates after creating a dashboard really surprised me. They helped me dive deeper into the data without having to think about what to ask next. It's almost like having a built-in consultant guiding you through your analysis. Very useful!

The fact that ChartGen can generate a chart and provide insights in just minutes is incredible. It feels reliable, efficient, and it’s exactly the type of tool I’ve been looking for to streamline my data work.

Congrats on launching your product! Can the platform create one single chart combining different data sources (for example, GA4 + Hubspot + Mixpanel)? What does make you different from established industry players like Zoho Analytics?

This actually solves a real pain point for marketers. Nice work

I’ve been testing it today, and honestly, it’s doing exactly what I needed.

When you’re merging Facebook, TikTok, Shopify, and GA exports, the scale pain is schema drift plus metric mismatches that quietly produce “pretty but wrong” charts.

Best practice is a typed ingestion layer (canonical schema + unit normalization), fast in-process compute (DuckDB or Polars/Arrow), and automated data-quality checks (Great Expectations) with provenance links from each insight back to the exact rows.

Do you maintain a semantic metrics layer per connector, and can users inspect or override the generated transformation SQL so dashboards stay reproducible over time?

I really like how ChartGen lets you ask follow-up questions after creating a chart. It feels completely natural and allows me to further customize the chart to get deeper insights, rather than just having a static visual. It’s a nice feature that adds a lot of flexibility

Huge congrats on the launch! 🚀 Ada looks like a powerful way to turn messy data into clear, actionable reports for busy teams.

Congrats! Looks cool - are charts then an image than can be copied? Or pdf download?

For me, the dashboard generation feature is the real standout. It’s incredibly easy to use and helps me compile and visualize data all in one place, making it easier to share insights with colleagues or clients.

I decided to give ChartGen a test run by uploading a basic CSV file, and I was honestly blown away by how clean and accurate the bar chart came out. The output wasn’t just quick, it was really well-organized and visually appealing. Definitely exceeded my expectations for a quick tool!

does the AI handle messy naming conventions automatically, or do I need to prep the data columns first?

Congrats on the launch! Is it focus on giving insights for marketing data or for more generic data analysis?

Congrats on the launch! You’re solving a real pain in the right way.
At Buk, we’re building an in-house analytics module for our HR clients. The UX/UI of ChartGen AI is quite inspiring! I’ll use you as a reference for analytics 🙂

By the way, did you use a SaaS/AI tool to create the promotional video? It looks amazing!

Congrats on the launch! I tried it out, and l like the chart as well as key insights generated.
One suggestion is to ensure that the key insights would be mobile friendly. When I tried using the sample Finance.csv, the key insights were cut off.

I tested this on a pretty large marketing dataset and really liked it. The suggested visualization options and follow-up questions were very helpful and made it easier to dig deeper into the data and spot new insights.

Great product, as most people were addicted to text, which creates a problem in decision-making, while visualization can help people to make decisions fast.

I’ve been using Ada.im for a while, and seeing it evolve into something like ChartGen is genuinely impressive. You can tell the team understands real data workflows, and this feels like a very natural next step!

Nice idea. Turning raw data into charts is easy — turning them into insights is the hard part. Curious how much interpretation vs visualization happens under the hood.

Do you plan to support auto-detected insights or recommendations (e.g. “this campaign is overspending” or “this channel is trending down”) on top of the charts? Congratulations!!

Congrats on the launch. I love the creativity of the last gallery image where the ChartGen mascot meets the Product Hunt mascot. :D

Are these exportable to Google Sheets? By the way, congrats on the launch.

Could you point me to the integration page?

Here's the link for everyone like me who got directed straight to ada.im:

https://chartgen.ai

Hi Product Hunt, Garry here. I’m excited to help launch Crustdata (YC F24)'s newest product: The WebSearch API.

It lets you search the whole web via a simple API, making it accessible for AI agents, products and tools. 

Think of this API as the fundamental layer on which you can build any tool that needs public web info (people, companies, posts, pricing pages, research articles, docs, blogs, etc). 

Why it matters:

The web wasn’t built for AI agents. It was built for the human eye. Inconsistent HTML, CAPTCHAs, and brittle scrapers make the web hard to use as input for agents.

As a result, agents lack vital qualitative information and cannot perform even simple tasks without accessing information from the web.  

The WebSearch API returns search results and page content as clean, predictable JSON you can use as input for AI agents, workflows, and apps.

What you can build with it:

1. AI recruiting tools: Find candidates such as researchers and engineers from public work (papers, GitHub profiles).

2. AI SDRs and GTM agents: Find more information about prospects from podcasts, blogs, forums, and feed this into personalized outreach workflows.

3. Competitive Research Tools: Track competitor pricing, product launches, and market positioning so you can detect opportunities and risks.

4. SEO Tools: Pull meta data, citations, and ranking data without building fragile scrapers.

5. Investment agents: Aggregate company information and market sentiment from news, blogs, and product pages to spot investment opportunities and risks.

6. AI coding agents: Fetch and parse the latest documentations, recent library updates so they can generate accurate code. 
   

How to integrate into your AI agent or tool:

Get started in under 60 seconds. Add these lines of code with your API key to access the entire web as structured JSON:

curl 'https://api.crustdata.com/screener/web-search?fetch_content=true' \

 --request POST \

 --header 'Content-Type: application/json' \

 --data '{

 "query": "Open AI recent product launches",

 "geolocation": "US"

}'

That’s it. It’s as simple as that. 

For non-technical users:

If you aren’t comfortable with coding, don’t worry. Our documentation is written to work with AI coding assistants like Claude or ChatGPT.

Simply:

1. Copy our API documentation

2. Paste it into Claude Code or Cursor

3. Describe what data you need in plain English (e.g., "Find all TypeScript developers who contributed to Next.js projects")

4. Let the AI generate the API call for you

5. Get working code you can use immediately, without writing a single line yourself
   

Example data you can find with this API:

For Sales: 

• To find specific pain points or angles to personalize messaging through information from a funding article: 

Search query: {founder name}  site:techcrunch.com

• To find specific pain points or angles to personalize messaging based on information from blogs or podcasts the prospect appeared on: 

Search query: {founder name} “podcasts” “blogs”

For Recruiting:

• To find engineers with a specific skillset from Github: 

Search query: "i'm a" "frontend developers" "react" site:github.com

• Finding researchers by publication topics: 

Search query: "machine learning" "interpretability" site:arxiv.org

For Market Research and Investment:

• To analyze the recent market sentiment of a company: 

Search query: Salesforce AND (sentiment OR review OR "market perception" OR "analyst sentiment")

Date range: startDate: July 13, 2025 | endDate: Jan 13, 2026

• To surface product launches or interesting events about a company:

Search query: "lovable AND ("product launch" OR "new feature" OR "beta" OR "partnership" OR "introducing") site:lovable.dev"

For AI coding agents: 

• To track library updates and changes:

Search query: "React 19" AND ("breaking changes" OR "migration guide" OR "what's new")

Key Features and Differentiators:

• Fastest WebSearch API with the subsecond latency

• Most accurate WebSearch API compared to other Web APIs

• Access the latest web pages indexed within minutes of being updated and available in search results

• Results from hundreds of sources from the web for one query

• Filters to control results (language, location, site/source, date ranges)

• APIs built for production with high throughput
  

Thanks for your support!

Excited for this launch!

Really interesting approach. Curious how teams think about keeping signals fresh as web content changes quickly.

Congrats on the launch! Crustdata looks perfect for powering serious, real-time GTM AI agents.

Great launch! Good luck today 🚀🏅

This is huge! Congratulations!!!

Great product. In an AI era it is must to get the updated info.

Do you have examples of teams using this without writing any code at all?

Congrats on the launch. Are these embeddable on the websites as well?

How are you thinking about rate limits and cost predictability as agents scale and make frequent web calls in production?

Been a user, it works great!

Congrats! What has been the most popular use case among your users or customers?

Is an hour the buffer time or can it even provide real-time updates? Example, some news broke a minute ago?

ooh this interesting!

Love the simplicity here! Building and maintaining internal scrapers to bypass CAPTCHAs is a nightmare for small teams. I’m curious: How do you handle the freshness of the data? Is it crawling in real-time when the API is called, or are you serving results from a pre-indexed cache? For a high-frequency tool like a price tracker or a daily research agent, what’s the typical latency we should expect?

Hi Product Hunt 👋

Shyjal here from Micro.company, maker of LocateStore.

While working with many businesses, we kept seeing the same issue: Building a store locator is still far more complicated than it should be.

Most teams already manage store locations in a spreadsheet. But to put those locations on a live map, they end up dealing with map API keys, custom development, agencies, long back and forth, and ongoing maintenance. All for something that should be simple. So we built LocateStore.

LocateStore lets you manage all your store locations in a Google Sheet. Store name, address, contact details, website, tags and more. From that single sheet, LocateStore automatically creates a clean, interactive, mobile friendly store locator with search and filters. Any update in the sheet reflects instantly on the live map.

No code. No API keys. No maintenance.

How it works is simple.
- Sign up to locatestore
- Add locations to a Google Sheet
- Copy-paste a small embed snippet into your site

That’s it, your store locator is live.

We built LocateStore to keep store locators simple, easy to understand, and fast to set up. It is designed to deliver a smooth “find a store near me” experience and is already powering 1000+ businesses.

Would love for you to check it out, try it, and share your feedback.

This saves me so much manual effort—a big win for me.

This is a really satisfying idea - “a Google Sheet becomes a store locator” is exactly how most small teams already work. The no-API-keys, no-maintenance promise is a huge win.

I’m curious how it behaves once it meets real-world data though. Addresses are often messy, duplicated, or half-filled - do you do any validation/cleanup, or is it strictly “whatever’s in the sheet”?

Also, if someone has a larger list (say, a few thousand locations), does the map stay snappy and readable? And can the embedded map be styled enough to feel on-brand, or is it intentionally minimal?

Congrats on the launch - this feels like one of those tools that saves you an entire weekend the first time you need it.

Love the simplicity of the concept, going from a simple, accessible datastore to a embeddable web component. I honestly kind of want to use this just personally to create a map of my favorite places around town.

Nice launch :), this feels very practical. Curious how people handle frequent or seasonal updates with it.

Hi PH community, 👋

Managing store locations shouldn’t require a developer. That’s why we built LocateStore to sync directly with Google Sheets.

Instead of showing customers a long, static list of addresses on your “Contact Us” page, LocateStore helps you add an interactive map that makes it easier to find nearby locations and can increase the chances of visitors actually walking into a store.

You can check out the live demo here:
👉 https://locatestore.com/demo

I’d love to hear your thoughts:

• Do you prefer maps over lists when searching for a business?

• Does an interactive locator influence your decision to visit a store?

Cheers,
Aslam from Micro.company

Turning a live Google Sheet into a locator gets tricky at scale: Sheets API quotas plus geocoding churn and 1k+ pins can tank TTI on mobile.

Best practice is to precompute and persist canonical lat,lng in the sheet, batch geocode server-side with caching, and ship a CDN cached JSON feed with marker clustering or viewport based loading.

What geocoder and maps stack are you using to keep it truly “no API keys,” and how do you handle address normalization plus rate limits when rows change frequently?

This solves a very real ops problem. Spreadsheets are still the backbone of many multi-location setups, so building on top of Sheets makes a lot of sense.

Is this meant for businesses that have offline stores and want to show their locations on their website??

It's almost refreshing to see such a simple (at least in concept) product doing so well and receiving so much attention. It seems the AI-wrappers steal the show the majority of the time, but something like this is TRULY useful and can be used with certainty. Amazing.

Hey Product Hunt! 👋 We're Notte (YC S25), and today we're launching the automation tools we wished existed when we started building browser automations.

Why we built this

Most real workflows need both deterministic scripts (for the reliable parts) and agents (for handling variation). Today you're forced to choose between:

• Black-box agents that look magical until they silently fail

• Fragmented DIY stacks where you juggle infra, orchestration, and app state across tools

There's a psychological gap too: when tools give you visibility and control, you debug and improve. When they hide the mechanism, you just assume "agents don't work" and abandon them. We wanted one environment where you can go from "I have a task" to "it's running in production" without context switching, and where building agents feels more like craft than simply prompting.

What the Console gives you

• 🎬 Demonstrate Mode – Just do the task manually once. Notte records every action and generates production-ready automation code. No prompts, no syntax guessing. Show your workflow, get editable code.

• 💬 Agent Mode – Describe what you want in natural language. The agent executes it in a live browser session; click "Map to Script" and it becomes editable code you own.

• 📝 Code Editor – Write automation scripts with a live browser beside your editor, AI code assistance, and rich debugging. See exactly what's happening as your code runs.

• 🚀 Zero-Config Deployment – One click to deploy your script as an API endpoint, with scheduling and cron. No infra setup.

Built-in agent tooling

• Managed identities (auth, 2FA, account setup)

• Secure vaults and proxy rotation

• Session management and managed infra

• Live debugging and execution logs

Who this is for

Devs (or vibe-devs) who need browser automations that actually work in production, whether it's data extraction, form filling, testing, or integrating with apps that don't have APIs.

We're a small team obsessed with developer experience and making agent tooling feel empowering instead of opaque. Would love your feedback in the comments!

👉 Try it free: http://console.notte.cc

– nottelabs team:) 🌸

Great product!

biased but this has genuinely been super useful + intuitive for me 🔥 can pretty much automate anything I can think of

When workflows change later like a small UI update or an extra step added by the site how easy is it to update just that part of the recorded flow without redoing everything from scratch or risking downtime?

congrats on the launch!

@ogandreakiro congrats on the launch

One thing that usually breaks browser automations is not knowing what went wrong when something fails. Being able to see the browser live, step through the actions and edit the code directly makes a big difference. That level of control is what helps turn an automation into something you can actually maintain instead of restarting from scratch every time.

​Finally, a tool that handles the mess of proxies and session management through one API. It saves me so much time on the infrastructure side

A lot of browser automation tools fall apart right after the demo. You can record something or prompt an agent but turning that into code you trust in production is the hard part. Demonstrate Mode looks like it’s trying to close that gap by letting you show the task once and then work directly with the generated code. That focus on visibility and control is what usually decides whether an automation actually ships.

Great product, need to give it a shot.

my favorite api for browser automation

Looks nice. BTW, how it works under the hood? does it use some kind of Playwright based automation or headless browser?

Hey Product Hunt! 👋 I’m Lucas, co-founder at NotteLabs.

With Demonstrate Mode, you show the browser what to do once. Notte converts that demonstration into deterministic, production-ready automation you can iterate on, deploy, and rerun at scale.

Everything is powered by the open-source Notte framework (github.com/nottelabs/notte), which gives agents a structured way to interact with the web. Full docs are at docs.notte.cc. Excited to see what you build 🔥

Looking forward to seeing what people are gonna build with this 🔥

@ogandreakiro andrea_pinto Love the hybrid “Demonstrate → editable script” + Agent Mode; at scale the hard part is selector/DOM drift + auth/2FA fragility that causes silent flake across thousands of runs.

Best-practice: generate resilient locators (ARIA/role/text + fallback strategies), snapshot+diff the DOM, run canaries, and enforce idempotency/anti-dup guards (especially for form submits) with durable retries.

Open Q: how do you version/replay sessions for debugging (video/trace + DOM snapshots), and can vault + identity access be scoped per workflow/tenant with audit logs? 🔥

I have used Notte for quickly building web agent automations. Excited to use Demonstrate Mode to iterate faster!

For quite some time, I believe web or UI agents that allow user to demonstrate use and AI auto correct are the ones that have highest reliability while minimizing maintenance cost. Notte's feature set is very close right now.

Demonstrate Mode helps bridge the gap between trying something out and actually using it in production. For me, recording a task once and getting real code I can edit solves a problem I keep running into with other automation tools. Creating the automation, testing it in a live browser and deploying it from the same place keeps everything in one flow. That last part is usually what’s missing when I try to move browser automations into production.

First calendar AI assistant which works properly 🎉🎉🎉 I'll soon stop typing and scrolling and only use voice, such a relief. My favorites are different summaries, searching, adding calls quickly, reminders, and color-coding. I still need to test accessing data via integrations.

Turning scheduling into a conversation instead of a UI maze is a smart move.

Looking forward to the Slack and ChatGPT integrations.

Going to try this for my challenge — scheduling across time zones and multiple teams, 15 emails deep, trying to find 30 minutes that works for everyone.

If it handles multi-person availability well, that alone is worth it. Congrats on the launch, Nick.

Congrats on the launch! Callum looks like a strong AI layer for real-world, multi-person scheduling across teams.

Congrats on the launch. It looks very ambitious!

@nick_ustinov1 Congrats on the launch! One thing I’m curious about: handling corner cases like last-minute conflicts, buffer times and priority trade-offs can be tricky for AI schedulers. Do you have plans or ideas around how Callum will tackle those as the product evolves?

Happy to see the product here with updated features that users always wanted. Kudos to the whole team on launch

Calendars are already crowded tools. The real value here feels like reducing coordination friction between people, not just scheduling itself.

Hey Product Hunt -

We just crossed 10 million developers on Netlify and wanted to mark it by building something people could actually launch.

Capsules lets you send a small digital payload—tied to a real Netlify project—into orbit around the earth, then discover other capsules overhead using your phone's AR.

Built in collaboration with community member, and Netlify power user, @leemartin and meant to be lightweight and fun. Curious what you’d send up.

Hey PH fam 👋

This one's personal for a reason I didn't expect.

We just surpassed 10 million developers on Netlify, and instead of writing about it, we asked ourselves: what would actually honor that number?

Not the metric. The people behind it.

This one needed to be for the community. So we built Netlify Capsules.

It's a way for every developer to take one of their projects, add something personal—a photo, a song, a note—and launch it into virtual orbit. Then use AR to find it floating in the sky above you.

What caught me off guard was how much the constraint mattered.

You only get a few words for your note. That forces you to ask: what do I actually want to say about this work? About this moment?

I've watched people spend five minutes on their payload and twenty on that note. (Looking at you Jacob!)

The AR piece shifts how it feels too. You're not scrolling a gallery. You're looking up. Your work is somewhere like a museum in the sky. Other people can discover it. It makes the digital feel physical in a way I wasn't ready for.

We didn't build this in-house. We asked @leemartin, a community member with 250+ deploys, to create it.

He's lived the builder experience we wanted to celebrate. That mattered.

What I love about this approach is it flips the usual dynamic.

We're not telling you what 10 million means. You're showing us. Through the projects you pick. The photos you share. The songs that got you through the build. The notes you write to express yourself.

Hope you'll check out the experience. Curious what you'll put in yours and what that choice says about the work that matters to you.

The Netlify team is here today so we would to hear if you've got questions and comments/reactions👇

Amazingly clever little build. Submitting a capsule was neat enough, but the mobile AR viewer is really next level. Kudos!

Netlify Capsules is EXACTLY the kind of product people have been saying they want to see more of - unique, playful and in the human spirit of creativity. When the same website template or AI generated copy is just a prompt away the team at Netlify have gone above and beyond partnered with one of their power users, @leemartin, and put love and delight into a fun celebration of reaching 10 million developers!

I'm always an advocate for these kinds of experiences and we should be encouraging more like them to push technology and human creativity further! 🚀

(Now back to exploring all the cool capsules I can find in the sky 🌌)

So beautiful and original way to celebrate the community 🎉
I've put my furry teckel into a capsule, she is orbiting out there 🤣

The location-based Web AR discovery is slick, but at scale you hit noisy GPS, WebXR support variance, and performance issues when dozens of capsules are nearby.

Best practice is to bucket capsules into an H3 or S2 grid, stream only viewport-relevant items, and optimize assets with glTF + KTX2/Basis texture compression plus LOD to keep frame times stable.

Are capsules anchored purely by lat,lng or do you also use WebXR hit-test anschoring, and what is the plan for opt-in location privacy plus anti-spam moderation?

🚀 Hey Product Hunt!

Andrew here. While building our IDE extensions and cloud agents, we kept running into the same problem many of you probably face when using coding agents in complex repositories: agents getting stuck in loops, over-apologizing, and burning time without making real progress.

We tried to paper over this with scripts, but juggling terminals and copy-paste prompting quickly became painful. So we built Zenflow - a free desktop tool for orchestrating AI coding workflows.

It handles the things we kept missing in standard chat interfaces:

• Dynamic Workflows: Workflows are defined in simple .md files, and agents can dynamically rewire the next steps based on what they discover mid-execution.

• Spec Driven Development: Use formal specs to guide agents, ensuring the implementation matches your architectural intent before a single line of code is written.

• Cross-Model Verification: Have Codex review Claude’s output, or run multiple models in parallel to see which one handles a specific codebase or task best.

• Blast Mode (Multi-Model Inference): Run up to four different models (Claude, GPT, Gemini, Codex) on the same task simultaneously. Compare their outputs side-by-side and pick the best result.

• Parallel Execution: Run multiple approaches on the same backlog item simultaneously mixing human-in-the-loop workflows for hard problems with faster “YOLO” runs for simpler tasks.

• Project-Level Kanban: Track and manage all agent work through project lists and kanban-style views, not scattered terminal windows.
  

What we learned building Zenflow

After running 100+ experiments on SWE-Bench and private datasets, we found that models are increasingly overfit to public benchmarks. Real-world success doesn't come from "smarter" models alone; it comes from the "Goldilocks" Workflow just enough structure to prevent loops without over-orchestrating the creativity out of the AI.

We’ve been dogfooding this heavily to build our own IDE extensions, and we’d love to hear how it handles your toughest repos.

Zenflow is free to use and currently supports Claude Code, Codex, Gemini, and Zencoder.

Exciting launch, crew!

You guys are really taking spec-driven development to the next level. I'm excited to see how it pans out. Let's gooo!

Huge congrats! Zenflow’s multi-agent orchestration and built-in verification feels like a game-changer for scalable AI engineering. I'm excited to try real workflows beyond vibe coding. Good luck!

I've been using it for a couple of weeks now and am now just babysitting the AI as it builds the product! Code quality is very good!

Congrats!

Multi-agent “blast mode” and dynamic rewiring is powerful, but at scale the pain is non-determinism: agents race, loop, and produce conflicting diffs that are hard to replay or audit.

Best practice is a reproducible execution harness: sandboxed per-agent workspaces/branches, deterministic step graph with idempotent tools, and mandatory verify gates (lint + minimal tests) before merge, with full traces for replay.

How does Zenflow represent and version the workflow state, and can it enforce conflict-free patch application plus automatic rollback when verification fails?

Hi Product Hunters 👋,

I'm Max,

I am coming from a non-technical background, from film production, and a bit more than a year ago I started building things that I like, that are useful for me, and that are fun.

I built Clippy because I wanted to have a cool way to dictate with local models and later I realised the whole GPT context copy and direct pasting possibility. And then ideas started storming with linear and co. I have a newer version with control of apple calendar and reminders, but thats still a work in progress.

And I chose Clippy for a vintage cute touch.

I did all the visuals myself in Figma and experimented a lot with liquid glass and local models.

Ah and as a fun fact - I coded around 90% of the app on airplane wifi, flying from Germany to SF. That was fun.

Hope you like it too.

Best,

Max

Is the extension safe? :D Lately I was trying more extensions and LinkedIn started accusing me I am using some not good tools so they restricted my account for a while. Because this looks like a cool tool but I do not want to risk anything :D

Congrats on the launch! Love the local-first, context-aware Clippy for frictionless in-app assistance.

very nice

I need clippy to knock on the screen to give me the full member berries

This is actually quite useful, could definitely unlock a lot of productivity in my day to day tasks 🚀 Thanks for sharing @maximilian_prokopp 🔥

Eliminating the 'copy-paste dance' between the browser and the text field is a huge UX win. It’s one of those friction points we just got used to, but didn't realize how annoying it was until a solution like Clippy arrived! The Linear and Google Calendar integration via voice is a game changer for productivity. My question: Which local model are you currently using for the 'context-aware' part? And is there a way for users to swap in their own models (like through Ollama)? Does Clippy 'see' the context of the specific app I'm in (like a code editor vs. an email client), or is it based on the text I've already typed in the field?

Coding 90% of the app on airplane Wi-Fi is the ultimate builder flex, thats an incredible story, Max.The liquid glass aesthetic in Figma really paid off and It’s clear that coming from a film background gave you a unique eye for the visuals the app looks beautiful! Only one question, are you planning to keep it strictly for macOS, or is a mobile companion app in the cards?

Context-aware “paste into active field” plus voice-triggered MCP tool calls can go sideways fast at scale: wrong-window injection, secure fields, and unintended side effects (Calendar, Linear) from misheard intent.

Best practice is capability-based tool permissions with explicit usaer-confirm steps and audit logs, plus OS-level allowlists and secure-field detection; for local dictation, streaming whisper.cpp-style on-device ASR with VAD keeps latency predictable and private

How do you sandbox MCP execution and prevent writes unless the focused app and target field pass an allowlist, especially around password or secure input contexts?

Great to have Clippy back ;)

👋 Hi Product Hunters!

I’m Brandon, co-founder of Conductor Quantum. Today we’re launching Coda, a natural language interface for quantum computers.

Coda lets you design, understand, and run quantum programs in natural language, without writing low-level quantum code. We built it because quantum computing is powerful, but still far too hard to actually use.

Quantum computers offer a new computing paradigm for simulating the world at the atomic level. This opens up new possibilities in chemistry, materials science, and drug discovery that push beyond what the largest classical supercomputers can handle.

The problem is most material scientists or biochemists can't use a quantum computer today - the barrier to entry to learn all the new bespoke tools, and the quantum information science is way too high. This is why we are building Coda.

Our long-term goal is simple: access to a quantum computer from every desk.
It’s built for domain experts and technical teams who want to explore real quantum use cases today and prototype faster. Also, it’s built for people new to quantum computing who want a practical, hands-on way to learn.

One of the first quantum computers we’re offering on our platform is Rigetti’s 84-qubit quantum computer, plus IonQ and IQM. We also support qubit simulations via IBM Qiskit and NVIDIA cuQuantum + CUDA-Q.

We’re early and learning fast, and we’d love your feedback.

Happy to answer any questions 👋

Congrats! Looks cool - what are strong use cases for quantum computers that LLM from laptop wouldn't be comparable?

Congrats on the launch! Love how Coda turns natural language into real quantum programs and removes low-level circuit pain.

Vibe-code quantum programs! Very cool to see this on ProductHunt. I don't pretend to have a deep understanding of quantum computing, but it seems like letting people actually play with it and build with it is the best way to help people learn.

Natural-language to quantum is awesome, but at scale the pain is correctness: LLMs can emit circuits that compile yet violate backend constraints or produce meaningless results under noise.

Best practice is to compile into a stable IR (OpenQASM 3 or QIR), run deterministic validation passes (type checks, qubit mapping, depth/cost bounds) plus simulator cross-checks and optional error mitigation (Mitiq) before hitting hardware.

What IR do you standardize on across Rigetti, IonQ, and IQM, and can users export the exact compiled circuit plus metadata so runs are reproducible across backends?

This looks awesome!!!

Congrats on the launch! StoryChief looks like a powerful hub for B2B content workflows and omnichannel publishing.

That's cool! Sometimes ideas emerge exactly when you see the big picture where all the elements are visually in one place. If you aim to target B2B Content teams (which makes total sense, as content is their important Marketing channel), I suggest to add an integration with popular task managers like Clickup/Jira/Trello.

Yes! 🙌 Unlimited brainstorming, but still clean and easy to digest!

Really proud of our team and looking forward to seeing how the community adopts this and hearing what early users discover!
LFG 🚀

Finally, teams and agencies can see the full picture, plan concrete actions and keep their voice consistent when working on their strategy!

Been testing AI Canvas for a few weeks and it’s such a life-hack for all marketers. Research → strategy → ideation → creation → improving → publishing all in one place instead of 10 tabs is a huge win.

Is voice input taken or does it have to be text-based prompting only?

Nice work, which AI api are you using? Why?

This is a relaunch with a set of updates added since the first release.

Over the past weeks, I focused on expanding flexibility based on early feedback:

• Added support for cloud AI providers (optional)

• Integrated LM Studio and Ollama for local LLMs

• Introduced custom prompts to fully control naming logic

• Added a multilingual interface

• Launched automatic file organization into category folders

• Improved batch processing and overall stability

Happy to answer questions or hear how people are using it.

Do you plan to launch this for iOS as well?

Yeah!!! Renaming files could be the worst task someone has to face, so I'm truly happy to see something like this and wish you all the best here!

Offline batch renaming hits scale pain fast: 10k+ files means slow content extraction, collisions, and nondeterministic names that make “undo” and dedupe scary.

Best practice is a deterministic pipeline: lightweight local parsers first (EXIF/PDF metadata), content hashes for stable IDs, preview + transactional apply with full rollback, and collision rules (suffixing, folder-level atomic moves).

How do presets encode the decision logic (regex + LLM + heuristics), and can users export a renaming manifest so runs are reproducible across Ollama, LM Studio, and cloud models?

This project originated from a real need. Internal documentation is almost always either outdated or in a poor format (KT sessions, spread out over several Google Docs + Lucid Charts, etc). I aim for Doclific to be a free, all-in-one solution to this problem.

Please, be brutally honest, would you use this? What other challenges do you encounter with documenting currently?

This could easily become a staple in my toolkit.

Woah, congrats man. This is awesome. I am so intrigued to play with this. We've been doing lots of work with docs lately

Docs-in-repo is the right call, but at scale the hard part is drift detection across monorepos where refactors and renames silently break code-linked snippets and diagrams.

Best practice is a CI gate that resolves references via AST/symbol IDs (not just file paths), runs link checks, and posts PR annotations with suggested doc patches plus a fail threshold you can tune per directory.

How are you extracting and versioning “smart snippets” (tree-sitter/TS compiler API, etc.), and can Doclific auto-open a PR with regenerated MDX when referenced symbols change?

The 'Docs as Code' approach is the only way to truly fight drift. Keeping docs in the repo ensures they undergo the same PR process as the code, which is a massive win for consistency. You asked for honesty: I’d definitely use this if it replaces the nightmare of syncing Notion/Confluence with GitHub. My question: (1) Since the docs live in the repo, how does Doclific handle non-technical stakeholders (like PMs) who might need to read or edit the docs without diving into the codebase? (2) Are these diagrams stored as code-based definitions so they are version-controlled, or are they handled differently? When code changes significantly, does Doclific have a 'check' or 'alert' system to remind engineers that a specific doc or snippet might now be 'drifting' and needs a re-prompt?

At scale, webcam-based micro-movement detection will face calibration drift (lighting, camera angle, fatigue) and false positives that can make the cyclic menu frustrating or unsafe for critical actions.

Best practice is a per-user calibration workflow with adaptive thresholds, temporal smoothing, and a state machine with dwell + confirm for “destructive” commands, plus a plug-in sensor interface that logs signal quality for tuning.

How are you measuring and exposing accuracy metrics (false-accept vs false-reject) over time, and can the TCP sensor protocol support signed messages or local-only mode to avoid unintended remote inputs?

This app may be a life-changer for those who are paralyzed! Upvoted and good luck!

What inspired you to build this? :)

One more launch from AbleMouse, yay!!!!!
Man I just love your mission, @alexander_radzhabov

Upvoted!

This is super cool, excited to see people working on building solutions for the differently abled.

Hey everyone. I am co-founder of New Norm

We noticed something important: people are already talking to AI to think things through and gain clarity.

But mental clarity doesn’t come from conversation alone.

That’s why, instead of trying to build “the best conversational AI,” we focused on something deeper: keeping everything about a person in one connected place and making sense of it over time.

New Nörm creates a new norm for reflection, built on scientifically grounded AI agents trained on well established therapeutic modalities, developed with input from practicing therapists, and supported by a continuous memory that understands context as it evolves.

This memory doesn’t just store conversations.

It connects what matters, your thoughts, emotions, recurring patterns, and personal history, across AI guided reflection, journaling, and other sources we’ll add over time.

This New Nörm turns it into оur pride Mind Graph, a living, visual representation of your inner world. Visualization helps people gain insight by showing how experiences, beliefs, and emotions shape how life is interpreted.

We bring this approach into a technical, interactive system that can be explored, questioned, and built upon.

You can return to any point, see how things connect, ask New Nörm to explain those connections.

Been waiting for something like New Nörm for a long time. 🔥

I haven’t tried it yet, but I’m genuinely excited about the idea because this is exactly the problem I’ve been trying to solve in a messy way for years: journaling across random notes apps, paper notebooks, and… my head (which is the worst storage system 😅).

What I love about New Nörm’s direction is that it’s not “just another journaling app.” It sounds like a space for emotional clarity — where your thoughts, emotions, and experiences stay connected over time, instead of getting scattered and forgotten. The combination of psychology + guided reflection + smart journaling + visual memory maps feels like the right approach for how the brain actually works.

This feels especially valuable for founders and high-output knowledge workers: when you’re carrying a million decisions, emotions, conversations, and stressors, clarity becomes a performance advantage. Tools that help you think better and process faster compound over time.

Big congrats to the team on the launch — love the mission, love the concept, and I’m rooting for this to become one of those “quietly essential” tools that serious builders use daily. 🚀🙌

L O V E the idea and the product! As someone who is always looking for ways to manage the high mental load of the startup world, New Norm feels like a breath of fresh air.

While many apps try to solve mental clutter with generic AI chats or static lists (duh, boring), New Norm understands that our thoughts aren't linear - they’re connected. And they must be mapped! The Mind Map is a total game-changer for me. Most reflection tools feel like a black hole where you pour in thoughts and never see them again (yup, that's true). Here, the visual mind map actually connects the dots and helps your brain to see the bigger picture. It’s helpful to see how a specific stressor from three weeks ago relates to a win today. It transforms the abstract chaos of a busy day into a clear, visual landscape. Seeing my emotional patterns mapped out in real-time feels less like journaling and more like architecting my own mental state.

If you’re a founder, a high-performer, or just someone trying to make sense of a busy mind, this is a must-try. The visual clarity you get from the mind map alone is worth the download. Huge congrats to @diana_oganesian @levon_hovhannisyan and the team on this launch! 🚀

Great product. Congrats, team!

Congratulations and best of luck on Product Hunt!

Hey New Norm Team. Do you think, one should still talk to a therapist, if they use New Norm intensively?

Congrats on the launch 🚀

Just curious — how do you plan to validate effectiveness scientifically?

Congrats on the launch! 🚀

Question - Are you planning integrations with therapists or coaches?

Congratulations and best of luck!

Hey team, congratulations on the official launch! Are you planning to include some sort of breathing/mindfulness/meditation exercises in the future for times when this subtle action might help regulating the nervous system, or is that not something that you envision for New Norm?

Is this suitable for people already in therapy?

Wow, I love it! Does it mean that AI can understand human emotions better than we do ourselves? (personally, I don't always have full clarity on what I'm feeling, so I find the product useful 😁)

A continuously updating “Mind Graph” will hit scale pain around privacy plus safety: sensitive journals, model hallucinations, and graph nodes drifting or merging incorrectly over time.

Best practice is client-side encryption with minimal telemetry, transparent provenance on each node/edge back to the exact entry, and crisis-aware guardrails with tested escalation paths.

How are you storing and versioning the graph (property graph vs embeddings-only), and can users export or audit the exact transformations that created each connection?

Question to builders: How do you plan to evolve the Mind Graph in future updates - e.g., adding more therapeutic modalities, custom node types, or deeper integrations like importing from other journals/apps?

Hi team, are there any features you’re excited to add next?

Congrats, team!
I have one question. How does New Nörm remember me differently than other apps?

Looks good, Congrats!.

By the way, what are the main differences between New Norm AI and ChatGPT in terms of features, use cases, and accuracy?

How does the guided conversation work – is it scripted or adaptive?

What makes New Norm scientifically grounded rather than just reflective writing?

How does New Nörm “remember/know” me differently compared to other apps?

Hi team, considering that everything is stored in a continuous memory, I wonder what privacy or security measures should users know about?

Is this more like a journal, a therapist, or an AI companion?

Hey team! How is the Mind Graph created? Is it automatic or needs manual input?

What problem does New Norm solve that existing mental health or journaling tools don’t?

What I like about Tivazo is the “all-in-one” approach that doesn’t immediately feel like heavy enterprise software: projects + time tracking + attendance/time-off in one place, with real-time visibility into who’s working on what. For teams that are remote/hybrid (or juggling freelancers), that single source of truth is usually what’s missing — not another standalone tracker. The onboarding-friendly positioning (and free tier for smaller teams) also makes it easier to actually get adoption, which is where most productivity tools fail.

I also appreciate that you’re being explicit about monitoring being optional, and the privacy angle (masking/blurring sensitive info) is the right direction — transparency + user control is the only way screenshot features don’t turn into “micromanagement vibes.” Curious question: do you have team-level privacy controls (e.g., role-based access, per-project rules, or “focus time” periods where screenshots are disabled) to help managers use it responsibly while keeping trust high?

Congratulations! Do you specialize on teams or the tool would work for personal use as well? To track time spent on task for freelancer

Very nice!

Congratulations

Congratulations on the launch 🎉 🎉

Nice launch! Curious, which kind of teams do you seem to see the most success with so far, remote, hybrid, or in-office teams?

This feels quite close to the direction we’re seeing with tools like Work-Break, focusing on productivity without turning it into micromanagement.I like that you’re positioning Tivazo as human-first and keeping monitoring optional. Curious how teams usually balance visibility with trust over time as they grow?

All-in-one time tracking plus optional screenshots gets tricky at scale: high-frequency events and images create storage costs, plus trust issues if access is too broad.

Best practice is on-device redaction before upload, strict RBAC with purpose-limited views, short retention defaults, and an append-only audit log so employees can see who viewed what and why.

Do you support per-project policies (sampling rate, focus-time no-capture, retention) and can admins enforce client-side masking to prevent raw screenshots ever leaving the machine?

Congrats on the launch!

Love the all-in-one concept. What advantages does Tivazo have over the conventional time-tracking tools in terms of productivity insights?

Interesting. How do you perceive screenrecording of the employees? Isn't it a lack of trust?

Can teams choose what they track and what they don’t?

Nice app. Are there plans to add AI-driven productivity insights?

What problem were you most focused on solving with Tivazo?

Wow, it is very simple and easy to setup productivity tool. Are there any plans to add more integrations in the near future?

Founder-to-founder: bringing work, tracking, and automation into one place is hard, but incredibly valuable when done right. Tivazo looks thoughtfully built for teams that want clarity without complexity. Congrats on the launch and wishing you strong early traction.

Congratulations on the launch!!
Interested in finding out how the teams react to the real-time insights in the long term.

Nice launch! Curious, which kind of teams do you seem to see the most success with so far remote, hybrid, or in-office teams?

Congrats on the launch, Nikhil and team. Tivazo feels like it’s built from real team pain, not just feature checklists. The focus on visibility without forcing micromanagement really stands out, especially for mixed setups with remote, hybrid, and freelancers.

I like that monitoring is optional and that you’re being upfront about privacy controls. That kind of transparency usually makes adoption much easier on real teams. The all in one approach for tasks, time, and attendance also feels practical rather than overwhelming.

Happy to support and follow along as you grow. Looking forward to seeing how teams use this in the real world.

Staying up to date with 3D, XR & AI should not eat up your evenings or weekends.

I hit that wall myself for months. So I decided to fix it.

Today I’m launching XR AI Spotlight, a weekly edition that cuts through the hype and delivers the tools, updates, demos, and deeper insights that actually help you understand and build in 3D, XR and AI.

You can take advantage of the exclusive Product Hunt discount here 👉 PH Launch Offer

Let me tell you why and what is included.

If you are in this space, you probably know how hard it can be to keep up with the latest news and updates.
You sift through endless newsletters repeating the same announcements, get hype reels with nothing you can actually use, and the news on AI covers only image and video models instead of the 3D and technological breakthroughs that will define the next generation of spatial products and experiences.

I’ve been curating this intersection for years, and more than 45K on LinkedIn and X follow my work because I stay hands-on with the tools and share practical insights they can apply immediately.

In addition to the weekly free interview with founders and creatives, Pro members will receive:

• A weekly Pro Edition with 10 handpicked tools, demos, research papers, and updates hard to find anywhere else.

• The Gaussian Splatting Handbook with an overview of cloud-based and local solutions to generate 3DGS, applications in VFX, gaming and real estate and more (available only until the 27th of January)

• Full access to the growing database of in-depth interviews, so you can borrow workflows, learn from their journey, and study go-to-market playbooks from top founders and makers in this space

Finally! As someone building LBE experiences (like YULLBE), I have absolutely zero patience for fluff. Most newsletters out there are just noise and hype reels. I need tools I can actully use in production. Gab, your content is one of the few sources that cuts the BS and delivers pure value to me. If you want to understand where 3D and AI are really heading without wasting your time, this is it. Keep pushing boundaries, Gab! All the best for toadays launch, Cheers, Marcus

I have followed Gab on LinkedIN for years and heard him speak at conferences. He is my absolute go-to expert for all things AR / VR / 3D, etc. I love his enthusiasm for the field and infectious curiosity. Really excited to see him launch this!

We build 3D scanning and 3D Gaussian Splatting tools at KIRI Engine, and we really appreciate what XR AI Spotlight is doing for this space.

In XR and 3D, the challenge today isn’t a lack of innovation, it’s cutting through the noise. With so many new models, tools, and demos, it’s hard to know what truly matters.

XR AI Spotlight does a great job curating what’s actually useful for builders.

Congrats to Gabriele on the launch. It is a valuable resource for the XR, 3D, and AI community.

Congratulations on the launch! This is an incredibly valuable resource for anyone working in or exploring XR, 3D, and AI. These fields are moving extremely fast. How do you decide which projects or signals are truly worth spotlighting week after week?

I love Gabriele's content, so knowledgable and interesting and direct - and XR AI Spotlight looks like an amazing evolution of that ethos!

How do you pick the guests for the interviews? There are a lot of tech oriented podcast and I am struggling to see a differentiator here.

I’ve been loving the interviews around Gaussian Splatting. Getting to know the founders who are building these tools has been incredibly valuable.

Weekly “top 10” in XR, 3D, and AI hits a scale wall fast: tool churn, duplicate announcements, and link rot can turn curation into noisy, non-reproducible picks.

Best practice is a structured ingestion + diff pipeline (GitHub releases, arXiv, vendor changelogs) with embeddings-based clustering for dedupe, source credibility scoring, and a human verification pass on anything you recommend for production.

How are you detecting meaningful updates versus rebrands, and will Pro members get personalization (tags like 3DGS, WebXR, Vision Pro) or an exportable feed so teams can track only what matters to them?

Cool, Gabriele! Looking forward to reading and exploring this amazing XR-AI space together, the future is augmented. 😎

I would really like to see the Gaussian splatting handbook (did a review and an upvote already ;-). Is there a subject on selecting the best workflow/pipeline for after doing the scan with let's say a portalcam?

Hi @gabriele_romagnoli excited to be here! Could you please be more specific when it comes to 3D, XR, and AI? What kind of topics are usually covered? I'm completely new to this, so any piece of information helps. Cheers!

Are the interviews shared on YouTube different from the articles shared in the free newsletter?

I worked with Gab during the first years at ShapesXR, trying to define the product market fit and his knowledge and experience in the field have been expanding enormously.
I also had a chance to join his podcast and talk about XR Design as a journey and career. The discussion felt more like a collaboration than an interview, a genuine exchange about how to break into XR design and how emerging technologies like AI are reshaping the way we think, create, and connect.

We built Pagesmith because most AI builders produce bloated React SPAs—fine for dashboards, but a disaster for SEO and AI discoverability. Our focus is on content focused websites.

Pagesmith is built on Astro. By leveraging an island architecture and shipping zero (or minimal) JavaScript, your content isn't trapped in a "shell." It’s instantly readable for search engines and AI agents alike. Plus, every site is deployed globally at the edge, ensuring lightning-fast TTFB (Time to First Byte) regardless of where your visitors are.

We’d love your thoughts on:

1. What features would make this your go-to for making websites?

2. How do you like the sites pagesmith generates?

Try it for free: pagesmith.ai

Congrats! Can I use Pagesmith to add / review an existing site or have to use it from the beginning?

Nice product. I really like the Astro framework. Do you have any authentication solution for the websites?

🔥 This is not another idea generator. This is a product builder.

Ideavize AI helps you:
💡 Generate real, deep-tech ideas
📊 Validate them with real market signals
🔥 Vibe code (not boring docs)
⚡ Execute fast
👥 Collaborate with your team
🚀 Ship real prototypes

From idea → validation → code → deployment
All in one flow. No chaos. No guesswork.

If you’ve ever had a great idea but didn’t know where to start —
this platform is for you.

Honestly feels like a 10X upgrade to how products should be built.

Try it. Explore it. Tell us what to improve.
We’re building this with the community 💙

Pitch-Deck creation is missing for presentation to the investors for funding support.

This is exactly what the startup ecosystem needs. Too many idea generators stop at the 'what if' stage, but the real challenge has always been the gap between concept and execution. The combination of market validation + actionable build plans + actual code is a game-changer. Would love to see how this handles the messy middle part of prototyping where most projects stall out. Are you focusing on any specific deep-tech verticals first, or keeping it broad?

I tested a few domains and technologies, and each time it produced unique project ideas which is a promising sign. I see the generated idea with tech stack, step by step implementation plan, research papers and a market analysis in a single tool, encouraging! I was hoping to see blockchain applied to the banking sector, but that option seems to be missing. I also, expected to see various graphs in market analysis.

Tried it for construction in the field of business intelligence, good insights and ideas that can be implemented on site business with key stakeholders.

With AI built in, options here just stay as an idea, but a great potential for a very good product. Look forward to diving into it more.

At scale, idea generators fail on trust: near-duplicate concepts, shaky “market signals,” and unclear ethics or IP boundaries as prompts get reused across users.

Best practice is a provenance-first pipeline: dedupe ideas via embeddings plus MinHash/SimHash, log every validation signal (trends, search volume, community chatter, repo activity) with timestamps, and generate a versioned build spec users can replay.

What exact signals do you score today for validation, and do you expose the dedupe report plus the step-by-step spec (code, deps, architecture) as an exportable artifact for audit and reuse?

Why should l use your app instead of general LLMs such as gemini, gpt or claude?
It appears to me that whatever this product is capable of can be done by those famous LLMs.
what is your product's unique value proposition?

Congrats on the launch!
the tool looks solid. I'll put it under some real stress over the next few days. In a world where more and more code is (and will be) written by AI, automated testing is only going to matter more

This application looks interesting, but I have a question: if, say, I record on a big screen, will it be later able to run the same test on a smaller screen successfully or I will need to create separate tests for each size? Thanks!

2 other notes:

• I think the link should lead to the main website not to the app sign-up page

• the plan from free to a paid looks a bit too steep ;-0

Hey PH 👋

I'm Vitalii, 20+ years in dev. Built this thing because code review was eating my life.

The situation: 8-12 PRs land every morning. Same patterns every time - check for null handling, look for N+1 queries, spot hardcoded secrets, verify error handling. Repeat.

By PR #10, I'm a zombie. And I still miss things.

So I built Git AutoReview. It's simple:

1. Open PR in VS Code

2. AI scans the diff (Claude, GPT, or Gemini — your choice)

3. You get suggestions with severity

4. Approve or reject each one

5. Only approved comments get published

The key part: AI suggests, you decide. No auto-commenting garbage in your PRs.

Works with GitHub and Bitbucket. GitLab coming next.

Free tier does 10 reviews/day. Should be enough to see if it helps.

Honestly just want to know - is this useful?

What would make it better?

Thanks for checking it out.

Cool! How to you handle the privacy?