Products from July 28, 2026

Pascal is a 3D architectural editor that lets you create, edit, and present building projects directly in your browser. It solves the problem of complex, inaccessible 3D tools by offering an intuitive canvas to scan, sketch, and visualize spaces instantly. It's designed for architects, homeowners, game designers, developers, and anyone who needs to work with 3D spaces without a steep learning curve.

GeoLibre is a free, open-source GIS platform designed for the modern, cloud-native world. It solves the problem of complex, expensive, and desktop-bound GIS software by providing a lightweight, private toolkit that runs directly in your web browser, on desktop, mobile, and in Jupyter notebooks. It's built for analysts, developers, researchers, and anyone who needs to work with maps and spatial data without the overhead of traditional systems.

It's a systematic trading platform that transforms 5,000+ peer-reviewed academic papers into runnable Python strategies with clean, integrated datasets. It solves the problem of fragmented research, messy data, and complex implementation by providing a single workbench to backtest, modify, and deploy strategies. It's built for quantitative traders, researchers, and students who want to move from theory to live trading with industrial-grade tools and an active community.

Speech-to-speech is a platform for creating local voice agents using open-source models. It solves the problem of privacy and vendor lock-in by enabling fully offline, self-hosted voice interactions. It's designed for developers, researchers, and businesses who need to build customizable, private voice assistants and agents without relying on cloud APIs.

The AI Agent Governance Toolkit provides a comprehensive framework for securing and managing autonomous AI agents in production. It solves critical challenges in agentic AI, including policy enforcement, identity management, sandboxed execution, and reliability, directly addressing the OWASP Agentic Top 10 security risks. It is designed for developers, platform engineers, and security teams building and deploying reliable, enterprise-ready AI agent systems.

Book-to-Skill converts dense technical PDFs into Claude Code skills, making complex information instantly accessible. It solves the problem of slow, inefficient learning and reference by turning static books into interactive, context-aware tools. This product is for developers, engineers, and students who need to quickly apply knowledge from technical manuals and textbooks while they code.

AI-powered productivity for working professionals. Voice-to-structured notes, smart bookmarking, and file organization in one place. Stop switching between apps, save everything, find anything, instantly.

Create temporary encrypted spaces to share files securely without logging in.

Lamoom is a marketplace of agent apps that run inside your own Claude - not on our servers. Install one and it works in your files, with your data. Every run is yours to see. Publish your own loops and charge per run or monthly. $20 free credit to start.

Upgrade your website with customizable no-code widgets. Create interactive experiences with reviews, booking, chat, popups, countdowns, FAQs, media galleries, announcements, and much more, then personalize every widget and embed it on any website in minutes.

The average premium cardholder leaves up to $1,500 in credits and points on the table every year. Cardzen tracks every credit, perk, and multiplier across your cards, reminds you before anything expires, and tells you which card to use for every purchase. Ask the AI advisor anything about your wallet, get a daily digest of what needs attention, and stop paying annual fees for benefits you never use.

Phantom is a voice-first AI agent for macOS that is always accessible via the Mac notch. Instead of opening a chatbot window and moving work into a separate conversation, users speak or type from anywhere on their Mac, without interrupting their work. Phantom understands the relevant screen and app context and completes tasks directly within the user's workflow. The possibilities are only limited by the imagination of the user.

SUB/WAVE turns your music library into a real radio station: one shared stream, an AI DJ that picks tracks, reads idents and takes requests in plain language. Self-hosted, works with local LLMs, MIT licensed. Web, iOS, Android and desktop players.

Windows has no place for what's happening right now. ZenithBar adds a floating island to the top of your screen: playback controls for any Windows media session, your next calendar events, pinned apps and sites, a file shelf you can drag straight into other apps, and a visual clipboard history. It opens on hover, disappears during full-screen games, and processes everything on-device — no account required to use it. One-time purchase with a 7-day trial, not a subscription.

ou want a real Linux VM that: Boots in seconds, not minutes Has a desktop you can actually see Runs headless when you need it (same VM, no restart) Stays running even after you close the app Doesn't require a PhD to set up TinyBridge solves this. One command. Full Linux. On demand. Try - brew install tinybridge

Conduit automates guest conversations and the work behind it. Conduit agents reply across email, WhatsApp, OTAs and social, voice calls. Agents dispatch subagents to act inside your PMS and tech stack: dispatching cleaners, updating calendars, closing the loop. Agents learn from every interaction, and you can inspect every step. 140+ languages, SOC 2 Type II. 50M+ conversations and $3B+ in reservation value for 300+ brands including Marriott, Hilton, Nobu and Fairmont.

Most AI photo taggers upload your images to the cloud or bolt on as a separate tool. Tag Your Photos doesn't: -100% on-device (Gemma 4 12B via Apple MLX) — no cloud, no upload - Works directly on your Photos library — no exporting, no duplicates - Keywords land in Spotlight system-wide — searchable right from the iPhone/iPad home screen, not just inside the app - Stays general when unsure — no falsely specific guesses

Every time someone gets hired, applies for a mortgage, or leases an apartment, someone has to confirm they actually worked where they said they did. That means millions of calls, emails, faxes (yes, in 2026), to HR and payroll departments. Superunit's AI agents do all of that from start to finish. They research, call, email, fax and handle documents until the verification is done.

Run curl qsa.sh for a one-command external security scan of your server's own public IP — naabu, nmap + vulners, and nuclei map your open ports, service versions, and known CVEs, streamed straight to your terminal in ~30 seconds. See exactly what the internet sees of your host: no account, nothing stored. Free scans run live; paid Pro (all 65,535 ports, async) and one-time Deep (the full nuclei firehose, emailed) dig deeper uncovering vulnerabilities below the surface.

Pinery is the self-publishing studio for Mac. 2.0 adds Prose, an AI co-author that works from the pages you've already written — every edit arrives as a diff you accept or reject. Write, design, and export ePub 3 or PDF. Your files stay plain Markdown.

Company Brain for AI agents, Fragmented communication and data of a company which is left on channels Emails, Slacks, WhatsApp and LinkedIn connect it all in one place with approval layer attach so personal and works chats don't gets mixed and connect it with any ai agents simultaneously, where records are keep getting updated minutes by minutes and so AI agents are getting updated as well so use AI agents with less cost of context and don't have to repeat.

Most AI chat tools either answer badly or hand off a ticket and vanish. ChatBeacon AIX does both halves. Aria answers from your own docs and pricing, resolves 87% of chats, and escalates with full context when it can't. Agents then cobrowse the customer's screen, sensitive fields auto-masked, or jump to video with no installs. PictureData turns product discovery into conversation for Shopify stores. Flat per-seat pricing, no per-resolution fees. Cloud, dedicated, or on-prem. 14-day trial.

General Intelligence Architect — describe an app and watch it get built live.

Cercle is conquering the loneliness epidemic by bringing back connections with the people that matter most. Check in with yourself and share your mood with your close friends or your entire Cercle. Take the guesswork out of your friendships, know how they're feeling before that phone call or text. Your friends' mood updates live on your home-screen widget, so you know who needs you before they have to ask. Built after watching a series of close friends live and struggle in silence

Connect Claude, OpenAI, Gemini or Grok to Ycode and use your preferred AI directly inside the website builder. Describe what you want to change, and the agent can update designs, manage CMS content, and build or improve components for you

If you've ever shipped a launch and watched your copy get truncated, ignored, or misread — Firstpass shows you every surface a stranger meets your product on (the Product Hunt page, the leaderboard row, the Glaze Store grid) and pins handwritten crit notes to what breaks in each one, before you publish. The same tagline lives or dies differently depending on where it lands: PH gives you 60 characters, the Glaze Store caps at 40, the browse grid cuts near 33. Nobody checks — until it's live.

Cekura is the testing, observability, and self-improvement platform for production voice and chat AI agents. It simulates thousands of scenarios, catches failures, diagnoses the root cause, rewrites prompts and config, then re-validates with a full regression sweep. Unlike tools that hand failures back to your team, Cekura closes the loop by fixing the agent itself and proving the fix holds without overfitting.

Self-hosted Next.js/TypeScript boilerplate: full OAuth 2.1 + PKCE, API key management with zero-downtime rotation, usage-based Stripe billing, and Redis rate limiting. 7 modules, 300+ tests. One-time €79, no revenue share, no platform lock-in. The metering core is free and open source on npm.

We allow companies that operate in the physical world (home remodeling, roofing, trades) to automate inbound and outbound calling & texting and run multi-threaded campaigns spanning several weeks. Our AI agents can hold 100+ parallel conversations, speak in multiple languages and integrate into any CRM. We help put appointment scheduling, customer service & confirmation calls on autopilot and eliminate missed calls, slow speed to lead and insufficient lead follow ups for our customers.

Your agent writes files locally in markdown and HTML, the formats it already speaks. Liminal renders them as clean UI instantly and syncs to your team in real time. Share a link and everyone sees the same live workspace, editable in the browser. No sending markdown over Slack, no hosting your own HTML, no waiting on Google Drive. No MCP calls, no proprietary formats, no wasted tokens. Over time, it becomes a shared second brain for your team and every agent working with you.

A free, browser-only workspace for performance marketers. Upload a campaign CSV or connect Google Sheets to diagnose performance shifts, budget headroom, creative fatigue, experiments, and marketing response(MMM,Regression Model and Cannibalization check)—without sending raw data to a server.

Recipe Book is a video data platform where you can semantically search 25M+ clips, iterate on the results, and buy the exact dataset you need to train your model in one sitting. Search -> rate a few clips -> we train a probe on your votes to re-rank the whole catalog to your taste. No contact forms, no sales calls, $3/hour.

An AI circuit copilot that designs your project and sources the parts automatically — no electrical engineering experience needed. Describe it in plain language, get a verified parts kit, and build it staged from breadboard to soldered perfboard.

The gap between agreed dates and a signed contract is where freelance jobs die. Hardbook fixes it. Your client picks dates and signs the contract in one flow. No app, no account, no chasing. Built by a freelancer to stop deal decay and lock in work.

Most agents pass their evals and fail in production. Prefactor is the evaluation layer that closes the gap. We score every agent run in real time, surface quality regressions and drift as they happen, and show engineering teams exactly how their agents are performing at scale. Built for the teams shipping agents to customers.

Yes, we're calling it: After Effects for the web. Design vector animations from scratch in your browser, move faster with Motion Copilot AI, wire up interactivity with State Machines, and export production-ready Lottie + dotLottie. No desktop app. No dev handoff.