Glasshand gives your AI agents real iPhones and Macs to work on. Connect Claude Code, Codex, or any other agent, and it can rent a device with a single prompt. The hardware sits in our data center, and your agent uses it the way you would: posting on TikTok, booking an Uber, or building and testing iOS apps. Each device is yours alone for as long as you rent it. When you’re done, we erase your data and factory-reset it.
11 月 5 日 AI 新品榜
精选 Product Hunt 当日票数最高的 28 款 AI 新品,合计 3.2k 票。Glasshand 以 370 票领跑,Rerun、Living Brain 紧随其后;其中 27 款获 Product Hunt 官方精选。
Rerun turns your ChatGPT or Claude subscription into a team of AI coworkers. Each one has tools, a computer and a shared workspace, runs on a schedule or a trigger, and asks before risky actions. Now open-source (AGPL v3) and self-hostable.
Every AI conversation contains knowledge worth keeping, but most of it gets trapped in separate chats and tools. Living Brain captures that knowledge, connects it to what you already know, and turns it into a persistent memory that keeps evolving. Share that intelligence across AI models, apps, and agents through API, SDK, or MCP, so every new interaction builds on the last instead of starting over. Reuse memory across ChatGPT, Claude, Gemini, OpenClaw, Hermes, Cursor, Codex and more
Maritime gives AI agents their own cloud computers: persistent workspaces, disposable sandboxes, Linux and Windows desktops, and Android phones. Agents can run code, use browsers, and work in apps without APIs, with a human able to take over when needed. Whether you’re building a personal assistant or running thousands of tasks in parallel, Maritime handles the computers so you can focus on what your agent does.
When an AI agent stops to ask permission, Pushary sends the question to the person running it, in their Mac’s notch or on their phone. Lee’s agent asks Lee. Sam’s agent asks Sam. A rule can send a push to your infra repo to your lead instead. Answers from the phone, Mac app and dashboard are saved with a name, so when something breaks, one page shows whose agent asked and who said yes. Works with Claude Code, Codex, Cursor, Agy and Hermes.
Clocknext is a billing and monetization platform for AI-native apps and agents. It’s tailored for AI founders, revenue, and engineering teams, to track AI usage from your product in real time, turn it into billable metrics with flexible pricing plans, and monitor costs, margins, and profitability at every level.
This launch marks a new era for Bridge: one agentic meeting platform replacing the fragmented meeting stack. Bridge now brings scheduling pages, automatic preparation, video conferencing, live intelligence, AI notetaking, agentic workflows, and structured memory into one connected experience for people and agents. At the center of this launch is a new kind of video conferencing built for customizable AI agents to join and participant in meetings.
Tao Browser keeps each company, client or project in its own space with its own cookies and logins. Lock tabs with Face ID or Touch ID, block ads and trackers on your device, import from Arc. No account, no telemetry. Free on iPhone, iPad and Mac (beta).
Rainbrand builds and maintains shared brand context from your websites, brand guides and files. Give your agents the guidance and assets they need for marketing campaigns, websites, slides, email, video, and more. Keep that context current as your brands evolve. Use it with Claude, ChatGPT, Codex or Cursor, or build it into your product through the API.
Stitch.ai brings mail, calendar, contacts, tasks, notes, sheets, slides, boards, and files into one connected workspace. Stitchy, your AI assistant, works with you across it all. Dual workspace panels allow you to drag, drop, and Stitch anything to everything. Nothing gets lost. AI-powered Knots, Tags, and Connections keep your work organized and easy to surface. Everything is built in: no integrations or extra email clients to set up. Get your work done in one place, without losing context.
Wingmen finds people already showing they need what you sell: a post about the problem, a new hire, a job change. It scores who's worth reaching and why, writes the opener from what they actually said, and follows up on autopilot until there's a call on your calendar. Run it in the web app or straight from Claude with the Wingmen MCP. Built for founders, B2B teams and agencies.
Nemotron 3.5 Transcribe is an open speech LLM for intelligent transcription: a single model that transcribes 40 languages verbatim or in written form, with context, speaker attribution, and word timestamps, selected with a natural language instruction. It is the best open-weights model on the English and multilingual Open ASR Leaderboards.
Real email on the domains you already run on Cloudflare, without paying per seat or forwarding to Gmail. You, your team and your AI agents work from the same inbox, and agents get their own access instead of your password.
AI agents that fix API breaking changes in your repos. It is built for developers whose apps and agents depend on third-party APIs. These APIs change all the time, and one breaking change can take your app down in production. Okapi keeps your code up to date with every API it calls, so your app keeps working and your team stops chasing changelogs. Okapi works with any API and is 100% free.
Zerg AI's own coding harness, in evaluation beta. Ask for Vim or htop and the agent opens them in panes beside it. Panes can hold more agents, each on its own model. Available models depend on your sign-in route and provider access. Mac with Apple chips.
A simple SMS api that just works. Integrates in 100+ services including claude and chatGPT. AI-assisted campaign registrations. Human support. Also - 50% cheaper than Twilio
Cosyra is a mobile coding tool for iPhone and Android. Run any agent on your phone from a cloud Ubuntu terminal without managing your own VPS.
AI Employees by Easy-Peasy.AI 精选
Hire an AI team that splits the work and asks before sending
Hire AI employees by role: a Chief of Staff, analyst, designer, support rep and 15 more, or describe your own. Add your website and the team reads it. Brief everyone in a group chat: the lead splits the work, teammates reply in a thread and you get one write-up. By default, emails, calendar changes and app actions wait for your OK. Each employee has a memory, its own computer and routines that run on a schedule or when an email arrives. You can even call them. Your first employee is free.
Stenograf records calls without a meeting bot, then transcribes, summarizes and searches them on your computer. Supported Mac and Windows. Ask questions across meetings and check the cited transcript passages. Your recordings and complete transcripts stay local.
Pinku runs open models (Llama, Qwen, Gemma) on your iPhone, iPad and Mac with Apple's MLX. Download a model once and chat offline, even in airplane mode. No account, no server: your chats never leave your device. Free to start.
I’ve always found something quietly beautiful about brief encounters with strangers. Paws is a tiny room of other people’s cats, seen through frosted glass. Maybe one wanders over and presses a paw to your fingertip. Nothing to win. Just stay a while. 🐾
Save AI chats into folders with a title and summary, search them live, and reuse prompt templates with variables via Ctrl+K or //. Works on ChatGPT, Claude, Gemini, Grok and more, in 55 languages. Local-first; Free needs no sign-in.
MCPCore lets you build MCP servers without code. Drop steps on a canvas, add loops and error branches, test live in the playground and publish a secure endpoint for Claude, Cursor, Codex and any MCP client. Or import your OpenAPI.
Bambu Lab H3C is a next-generation 3D printer that makes multi-material printing faster and easier. Its nine-tool Swaptek system switches materials in as little as six seconds, with less filament waste and no repeated loading. Combine colors, rigid and flexible materials, and different nozzle sizes in a single print. With automatic calibration, integrated filament storage and drying, and support for soft TPU, H3C lets you focus on what you're making, not managing your printer.
Keel is a free, open-source Mac app for Redis 6+, Valkey and Dragonfly. Browse millions of keys with SCAN only, edit every core type, use a redis-cli-style console and read server health. Read-only connections and typed confirmations keep production safe.
Vibeconferencing puts your coding agent (Claude Code, Codex, Grok or a local model) into your call as a participant, with a face and a voice. It hears the room, talks back, and builds on a shared whiteboard while you talk. Works in Google Meet, Zoom, Teams, Slack huddles, WhatsApp, Telegram and phone calls. Free and open source.
A native notch and top bar for Windows (Linux preview). Media, quick tasks, Wi-Fi/Bluetooth, power and little animated scenes live at the top of your screen. About 1 MB, about 0% CPU idle, no Electron. Free and MIT licensed. The demo on the site is playable.
A macOS app that reviews GitHub pull requests with your local Claude Code. AI findings sit beside the diff, and you accept, reject or edit each one before posting. Every PR gets a 0–100 risk score, and an optional autopilot clears routine reviews while handing risky PRs to you with nothing posted. No clone and no API key to set up: it uses your existing gh and claude. Free and open source (MIT).