Shubh Saraswat

Raccoon AI - A general purpose collaborative AI agent

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.

Add a comment

Replies

Best
Lien Chueh

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?

Shubh Saraswat

@lienchueh Two things:

  • Any kind of knowledge work. Deep research with real sources and citations, competitive analysis, data analysis with visualizations, writing reports and documents, due diligence, literature reviews, market sizing. If it involves reading, thinking, and producing a deliverable, it handles it really well.

  • End-to-end projects chain multiple skills. It's that you don't have to context-switch. The agent has a full computer and remembers everything in the session. So the output of one task becomes the input to the next naturally.

DHEERAJ NT

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! 🎉

Shubh Saraswat

@dheeraj_nt do try it out and let us know your feedback, we have built it to be the best possible human-AI collaboration tool.

Kimberly Renee Knowles

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?

Shubh Saraswat
@kimberly_renee_knowles That's exactly the use case. It runs entirely in the cloud so you can pick up from any device with a browser. No local setup required. You can pull in your NotebookLM outputs and have the agent repurpose them for each platform, turn a podcast summary into a LinkedIn article, extract key quotes for Instagram, write YouTube descriptions and tags, generate thumbnails, video snippets, the whole pipeline. Twitter/X is a native connector so you can draft and post directly from a session. For other platforms, you can connect tools via custom MCP servers or use the built-in browser agent. It connects to 40+ services out of the box including Gmail, Google Drive, Notion, and GitHub, and you can add anything else you need. We also take requests from customers for native connectors. Code PH5X gives you a month of Plus 5x free to try it out.
Himani Sah

I think what I like most about this is the transparency of seeing every step the agent takes. Congrats on launch!!

Shubh Saraswat

@himani_sah1 Thank you so much, transparency is everything when you're trying to give agents autonomy to do everything for you.

Kumar Abhishek

The “agent with its own computer” concept is fascinating. Good launch!!!

Shubh Saraswat

@zerotox Thank you so much Abhishek! Do check it out and drop your feedback 🙏

Roop Reddy

The integrations list looks strong. Any plans to support Slack or Linear for team-based workflows?

Shubh Saraswat

@roopreddy We have a slack integration, you can install Raccoon AI into your workspace and collaborate on the same sessions with your team, it has all the context, like a teammate would, it is in private beta currently and you can install it from here: https://gateway.raccoonai.tech/oauth/slack/install. We would love your feedback on it.

Linear and Github are the next big integrations we are working on and they will be launching soon alongside the slack integration.

Nuseir Yassin

How do you prevent the agent from taking unintended actions with connected tools? 😅

Shubh Saraswat

@nuseir_yassin1 we guardrail sensitive actions on the agent level, and about the connectors:

  • Most connectors use OAuth or API keys with scoped permissions, the agent can only access what you've explicitly granted.

  • On top of that you can choose which tools you want to enable or disable for any particular connector, this way you can choose to give less privileged access to the agent even if the connector's scopes are broader.

Joe Dodridge

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!

Shubh Saraswat
@joe_dodridge Thanks for your support, and congratulations on your launch, there is definitely some synergy. I will check it out.
Aman Pandey

I have started using it and it is so smooth. Great start. All the best to Raccoon AI team

Shubh Saraswat
@aman_pandey16 Thank you so much, if you face any issues, lmk :)
Vedant Uttam

The managed workspace is really awesome, how can I, in sync with my team, work on a project?

Shubh Saraswat

@vedantuttam You can share your sessions with your team, and also publish any file or app the agent created on a public link to share with anyone.

We also have a Slack integration which you can connect and collaborate with your team on the same session by simply mentioning Raccoon AI in any thread.