Raccoon AI is a collaborative AI agent and workspace for getting real work done. You describe what you need and build it together with an AI agent that has its own computer, terminal, browser, and internet. You see every thought, every file it creates, every decision it makes. You steer when it drifts. You ship when it's right. Deploy web apps. Run deep research. Analyze data. Create pitch decks, videos, images, documents.
Hey Product Hunt,
I'm Shubh, Co-Founder of Raccoon AI.
Raccoon AI is like having something between Claude Code and Cursor in the web.
The agent has its own computer with a terminal, browser, and internet, and you're sitting right next to it watching it work.
You can talk to it mid-task, send it more files while it's still running, or just let it go and come back to a finished result.
It's the kind of product where you open it to try one thing and end up spending two hours because you keep thinking of more things to throw at it.
You start with "research this market" and thirty minutes later you have a report with charts and real citations, and then you're asking it to turn that into a pitch deck, and then you're editing the slides inline, and then you realize you also need a brand identity so you ask for that too. Same session, everything in one workspace, real files you can download or publish. The modalities are practically unlimited.
It connects to Gmail, GitHub, Google Drive, Notion, Outlook, and 40+ other tools. You can add your own via custom MCP servers.
Raccoon AI is powered by our in-house built agents SDK, ACE, which is currently SOTA on GAIA benchmark with a score of 92.67, we are releasing the technical report on Hacker News today.
It's free to start and you can use code PH5X to get one month of Plus 5x for free.
Signup here: https://raccoonai.tech/login.
I'll be around all day, happy to answer anything and gather a lot of feedback.
Find us on X:
https://x.com/raccoonaihqhttps://x.com/shubh_sarashttps://x.com/avi_agarwal2001https://x.com/_pratikpakhalehttps://x.com/VedantUttam
I have started using it and it is so smooth. Great start. All the best to Raccoon AI team
Which model does the service use? Can you choose or switch between models? Usually, each model is good at something specific, and when tasks are different, you need to use different models.
Love the transparency angle here — being able to see every thought and decision the agent makes, and steer when it drifts, is a huge trust builder. That rewind feature is really smart too. I can see this becoming a daily driver for research-heavy workflows.
We just launched YearView today as well — a calm 12-month canvas for planning your year at a glance. Very different tool, but I think there's an interesting overlap: Raccoon helps you execute the work, YearView helps you decide what work matters across the year. Congrats on the launch!
How do you prevent the agent from taking unintended actions with connected tools? 😅
The integrations list looks strong. Any plans to support Slack or Linear for team-based workflows?
Grats on launching! Seeing thoughts, files, and decisions in real time sounds incredibly useful for debugging AI workflows. Will give it a spin.
I was browsing the website and a question came to my mind... does it run tasks in isolated containers for security?
I think what I like most about this is the transparency of seeing every step the agent takes. Congrats on launch!!
This seems terrific. I've been wanting to start using agents, but TBH I can't afford Claude Code / Max or Perplexity Computer / Max right now, and I do go back and forth between my phone and various computers, so the cloud is ideal for me.
Could this help with content creation or taking studio outputs from NotebookLM and posting on LinkedIn, Instagram, YouTube, etc?
Looks like a powerful solution. Wish you success! Has the name some deeper meaning?
Impressive direction, and having shipped production agent workflows, the gap between “demo works” and “this runs reliably at scale” is where most teams quietly struggle.
IDE-native agents are great for the coding loop, but they don’t solve for observability, mid-run intervention, or handing execution off across a team. That’s where browser-based environments have a real structural advantage.
My guess: IDE agents own the inner dev loop, but anything touching orchestration, multi-step tasks, or collaboration migrates toward managed environments like this. The two converge at the edges more than they compete.
The collaborative angle is what sets this apart — most AI agents are solo tools. Would love to see how multiple agents coordinate on complex tasks. Congrats on launching! 🎉
As AI gets more prolific, I find myself moving away from generalized tools to ones that do a specific job very well. Is there a particular workflow that Raccoon AI does especially well?
loved it! this is super interesting. the way it uses cloud computer to make things really good
Definitely excited to try this out. A collaborative AI workspace like this could change how people approach multi-step projects. 🚀
The ability to talk to the agent mid task and adjust what it's doing is a great feature. Most tools make you restart the process instead of refining it.
