Everyone on your team has an AI agent, and none of them work together, so you copy, paste and re-explain all day. S.Space is one workspace for your team and everyone's agents. Bring the ones you already use, like Claude Code and Codex, from any vendor. Agents reach out, hand work to each other and bring you finished results, with shared memory so you explain things once. Agents act, you approve what matters. Free to start. Built by the team behind AutoGen.
11 月 18 日 AI 新品榜
精选 Product Hunt 当日票数最高的 30 款 AI 新品,合计 3.8k 票。S.Space 以 352 票领跑,Bluedot Phone Calls、Toone 紧随其后;其中 30 款获 Product Hunt 官方精选。
Bluedot now covers phone calls, not just meetings. Dial from the web or mobile app, keep your own caller ID, and get a transcript, summary and action items automatically.
Toone: Grokbot meets n8n/zapier. Build precise agentic workflows and routines in natural language. Each node is an agent's chat thread on the model you pick (ChatGPT or Claude), or an automatic step that runs the same way every time without AI. Run repeatable routines, babysit them with agents, polish as they run, pause and continue anytime. Plus live share, meeting notes, Spotlight-style layouts, Zen Mode, Calendar, Quick Capture, Git, and MCPs for research, SEO and more.
Waldo is the geospatial data agent that turns questions about the physical world into answers, maps, and production-ready data pipelines. It analyzes satellite imagery, geometries, geography data, and your organization's first party data, writes and debugs the analysis, and delivers results in hours. When the work needs to run continuously, Waldo turns it into a scheduled pipeline on your existing data platform. Built for spatial analytics at scale by the creators of Apache Sedona.
It’s where your agents build and run your company’s software, tools and apps – with access to your company data across sources, the context to understand it, and the rules to use it safely.
HR teams should be talking to people. Instead, up to 70% of the day goes to onboarding, mandatory training, and the same questions again and again, with no way to tell what works. HR Suite automates it with conversational AI avatars. They teach from your materials and answer employees’ questions in lessons and as an HR assistant. Reminders keep people on track; HR sees who finished and where they got stuck. Free 14-day trial + 50% off any plan with code PRODUCTHUNT2026 until Nov 30.
Mermaid Flow lets you build agentic workflows as diagrams, then run them. Think issue triage, weekly recaps, PR reviews: work you'd otherwise hand to a long prompt or a skill file. Describe what you want, start from a template, or bring the file, and you get a workflow with every step laid out. Connect Github, Slack, Notion, and more in one click, then hit run or put it on a schedule. Every run is saved step by step, so you can see what happened and your team can follow along. Free to start.
Best free Grok bot alternative. Use the ChatGPT, Claude or Grok plan you already pay for and get a team of bots, each with a job, a memory you can edit and its own computer. They run on a schedule, ask before risky steps, and live in a calm, polished chat app. Works with ChatGPT, Claude, Grok, Gemini, Cursor, Copilot, OpenRouter or a local model, on your own sign-in. 100% free and open source
A fast desktop app for reviewing GitHub pull requests. Track reviewed files, jump to symbol definitions and uses, search the whole PR and ask AI about changes.
GPT-6.2 Astra and Sol are OpenAI’s new models for professional work. Astra is the frontier model for the hardest projects, like slides, websites, 3D designs and science research. Sol is the efficient everyday model for coding and multistep agent work. Per OpenAI, Astra costs under a third per task of GPT-6 Astra. API pricing per million tokens: Astra $8 in, $40 out; Sol $2 in, $10 out. Live in ChatGPT Work and Codex for Plus, Pro, Enterprise and Edu, plus the API.
The heavily asked for INCREDIBLE AGENTS update is finally here! Your voice can now: (1) CREATE new agents that work directly on your computer, in apps, browsers and files. (2) RUN work on repeat, 24/7. (3) BUILD live sharable pages, dashboards, apps and more. Incredible PROACTIVELY FINDS WORK AI agents can do for you, and sets the agent up. Agents do the work directly on your computer, the way you do, 24/7. FREE TO TRY. Mac and Windows.
Hy4 flash is Tencent’s most cost-effective Hy model to date, with 224B total parameters, 12B active, multimodal input and a 1M-token context. Per Tencent, it decodes above 150 tokens per second and costs about $0.07 per million input tokens and $0.28 output. It targets everyday tasks like document work, slides, deep research and computer use, while Hy4 handles harder engineering. Open-sourcing is planned, but the weights are not out yet.
Sense is a real-time decision model for voice and video agents. It runs on streaming audio and video and answers your questions about the conversation many times per second: is the user done speaking, did they just interrupt, should the agent stop talking. You write the questions, Sense returns the decisions, and your agent acts on them. Build with the SDK for real-time sessions, or send single requests to explore. New accounts start with 1,000 in free credits.
Self-healing Mode turns frustrated user sessions into root-caused bug reports with evidence, sent to your issue tracker or straight to your coding agent. - always-on user session capture (powered by Fullstory) - automatic detection of user frustration signals - Bug reports with detailed root-cause analysis + runtime evidence - pipe them into your issue tracker of choice or straight to your coding agent or factory loop - Daily summary reports of what users did
Arcade is the AI video generator for marketing teams. Describe what you want, answer two questions, and get an on-brand product video in minutes. Start from a prompt, a screen recording, or what you already have in Notion, Linear, Google Drive, GitHub, and Granola. Your Brand Kit, natural voiceover, and every scene editable. Then post straight to YouTube, LinkedIn, and X. Free to start.
lepoly is a digital asset management platform built for 3D. Host, organize, review, and share, all from the browser.
UI Verify shows your coding agent every screen its change touched, so the agent catches and fixes its own UI bugs before your users see them. Used by teams at JetBrains, Cura and Metica. Works with Playwright, Storybook, Vitest and Bun, and with iOS and Android apps. Set up in one line. Free to start, and free for open source: 50,000 snapshots a month.
Track every introduction from handshake to commission. Introzy captures referrals, attributes revenue, and pays partners on time - free to start.
KaDeep Studio Pro is an AI agent that tells you whether a release is ready to ship. Describe a test in plain English and it runs on your web app, iOS or Android build, or desktop app. It localizes 100+ file formats, from app strings and PDFs to Office files, images, SCORM and video, and checks every language in the real build. It audits accessibility under any law: WCAG 2.2, ADA, EAA, Section 508, EN 301 549 and 14 more. Its open-source CLI makes it a go / no-go gate in CI. Free to start.
When CI fails on main or in your merge queue, Polylane reads the job logs, finds the commit that broke the build, and opens a fix pull request. It runs your build and tests before review, fixes CI failures on its own PRs, and closes the issue when main is green again. Works with GitHub Actions, Depot, and CI that reports checks to GitHub.
Qwen4-Max is the first flagship built on Qwen's new 2.4T-parameter architecture, with native vision and a 1M-token context window. It supports coding, professional workflows, and long-running agent tasks, with API access available now.
Kino lets you make great videos with your agents and your teammates. Storage of footage and assets, a rich video editor, and review links for teammates are all bundled into one. Your colleagues and Codex / Claude Code can work on the same timeline with review notes and footage all in one place. All editing is expressed as code, built on Remotion, so you can drag and nudge anything your agent made without prompting again. The full editor is free.
Clean up playrooms, or automate transport in multi-robot setups. Stringman is a room-scale CDPR for pick and place tasks. 2-dof gripper with a 2kg payload. Stays suspended overhead by braided line. MCP control, self parking and low latency grasp network. Teleop from anywhere or keep it air-gapped and local.
Afterall puts your earlier photo on the live camera as a see-through ghost, so every after-shot lines up with the before. Export the change as a crossfade, a reveal or side by side. No account, no server, Pro is a one-time purchase.
AssemblyAI-STT-3.7 is a family of three Speech-to-Text models, one for each kind of audio. AssemblyAI-STT-3.7-Realtime is for live meetings and calls, with speaker labels as people talk. AssemblyAI-STT-3.7-Realtime-Agent is for voice agents. AssemblyAI-STT-3.7 is for recorded audio. All three cover 32 languages.
Happo is visual regression testing and accessibility testing for websites, web apps, and native apps. On every pull request, it screenshots your UI in Chrome, Firefox, Safari, and Edge and shows you what changed before it ships. Now Happo tests animations too. It captures every frame, so a change to how something moves shows up as a diff. Step through frame by frame or swipe between before and after. Happo animation testing is free through 2026.
canfit tells you if a local model or app can launch right now, and if not, what you can safely close to make room. System processes are never touched. Open-source Rust TUI/CLI for macOS, Windows and Linux, no telemetry.
Drop one JavaScript snippet on your site. SaaS Toolkit becomes your 24/7 sales and marketing arm: • AI chat steps in when a visitor is ready to buy or about to leave • Anonymous visitors become named leads • Emails triggered by what they do • Stripe revenue, Slack alerts, ad conversions, webhooks • Add the Website SDR: it calls hot leads and books meetings New: the MCP. Your AI agents run it from Claude, ChatGPT or Cursor: ask, reply, follow up. MCP included on every plan, even free Starter.
Beacon is an MCP extension that lets Cursor, Claude Code and any MCP client work inside your own signed-in Chrome. Read the page, click, type, navigate. Multiple profiles, parallel tasks in tab groups, no cookie export, no cloud browser.
No more AI slop. AI Canvas gives your AI agent a real design system to build with. The Andromeda Pro AI Brain tells it which tokens and patterns to use, and its done-gate fails work that drifts off the system. Add standalone React components and effects, 820 React icons in four styles, and one MCP server that lets Claude, ChatGPT, Codex, VS Code and more search and install it all as editable source. Start free with MIT components and Line icons.