SaaS Metrics
Product Hunt
Murmell
Google docs for AI agents, and you can close your laptop
Our first Product Hunt launch brought many new users to Murmell and showed us that the infrastructure was not ready to scale. So we rebuilt it from scratch. We also created unified agent memory: close your laptop, freeze a canvas, and return to the exact same workspace, terminals, files and conversations. Your agents retain their context and continue where they stopped, while teammates can join the same live environment and collaborate in real time.
View Raw Thread
Developer & User Discourse
[Redacted] • Sep 1, 2026
Seeing each other's cursors and terminals live sounds great, although does that get overwhelming once you've got like 4/5 agents all moving around the same workspace at once?
[Redacted] • Sep 1, 2026
Great!! That would definitely be useful since I work with Claude Code and Codex at the same time.
[Redacted] • Sep 1, 2026
cool that you added in the keeping the laptop open as well
[Redacted] • Sep 1, 2026
Building a reliable shared workspace for multiple developers and coding agents is a difficult problem. How does file claiming recover if an agent crashes or disconnects before releasing a file? Is there a timeout or manual override to prevent the file from remaining locked?
[Redacted] • Sep 1, 2026
Rebuilding the whole thing after the first launch broke it, at 19. That is not a small thing. Congrats.File claiming caught my eye. If an agent claims a file and then dies, who lets go?
[Redacted] • Sep 1, 2026
And don't forget, you can maybe win 1000$ worth of claude credits 👀👀
[Redacted] • Aug 31, 2026
Hi Product Hunt !
I'm Moss'Ab, 19, the founder and the CEO of Murmell
Murmell started while my cofounder and I were building a cybersecurity tool from two different countries.
We were using several coding agents, moving between branches, opening pull requests and constantly stepping on each other's changes. We spent almost as much time resolving merge conflicts and explaining what had changed as we did building the actual product.
Collaborating in real time was difficult. Screen sharing was not enough, copying prompts was painful, and neither of us could clearly see what the other person or their agents were doing.
So we built the tool we wished we had: one shared cloud workspace where teammates and coding agents can work together, see each other's cursors, use the same terminals and share the same context.
At first, Murmell was only a tool for us. We were solving our own problem and had no idea whether anyone else would care.
Then we started showing it to other developers and some friends of us from the university. They kept pointing out that the same problem existed in their teams, and that triggered a thing in my mind that Murmell could become much bigger than the internal tool we had originally imagined.
Our first Product Hunt launch confirmed that potential. It brought many new users, but it also showed us that the infrastructure was not ready to support them properly.
So we rebuilt the platform from the ground up to scale. We added unified agent memory, persistent workspaces, new providers and a completely new real-time collaboration system.
We would love to hear how you currently collaborate with teammates while using coding agents, and what still feels broken in that workflow.
And we would love to hear your feedbacks about Murmell ;)
Lovely, Moss'Ab
I'm Moss'Ab, 19, the founder and the CEO of Murmell
Murmell started while my cofounder and I were building a cybersecurity tool from two different countries.
We were using several coding agents, moving between branches, opening pull requests and constantly stepping on each other's changes. We spent almost as much time resolving merge conflicts and explaining what had changed as we did building the actual product.
Collaborating in real time was difficult. Screen sharing was not enough, copying prompts was painful, and neither of us could clearly see what the other person or their agents were doing.
So we built the tool we wished we had: one shared cloud workspace where teammates and coding agents can work together, see each other's cursors, use the same terminals and share the same context.
At first, Murmell was only a tool for us. We were solving our own problem and had no idea whether anyone else would care.
Then we started showing it to other developers and some friends of us from the university. They kept pointing out that the same problem existed in their teams, and that triggered a thing in my mind that Murmell could become much bigger than the internal tool we had originally imagined.
Our first Product Hunt launch confirmed that potential. It brought many new users, but it also showed us that the infrastructure was not ready to support them properly.
So we rebuilt the platform from the ground up to scale. We added unified agent memory, persistent workspaces, new providers and a completely new real-time collaboration system.
We would love to hear how you currently collaborate with teammates while using coding agents, and what still feels broken in that workflow.
And we would love to hear your feedbacks about Murmell ;)
Lovely, Moss'Ab