This is really cool to see, reminds me of the early days of CodeSandbox. Though this API looks _fantastic_. I love that you do VM configuration using `with`.
We read your blogs when building all of this!
Launch HN: Freestyle – Sandboxes for Coding Agents
171–180 of 182 posts
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#172Is this similar to https://instavm.io/ ?
Never tried them, I think the weird thing about VM providers is the difference really all is in the execution. These guys seem great in concept but I don’t know enough about how they properly work.
Hi Ben, one of the founders of InstaVM here. Congrats on the launch!
Here is a feature tour of InstaVM https://instavm.io/blog/meet-instavm-infra-for-your-agents We would be publishing on the tech soon.
Would love to give you a demo of InstaVM and trade notes. Let me know abhishek@instavm.io
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#173[flagged]
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#174The memory forking is really interesting. I wonder if copy-on-write at the VM level, O(1) with respect to machine size, won't scale cost with how many forks to take, but 320ms median seems good for the branch-and-explore pattern without reprovisioning every time.
One gap I'm noticing in these comments and in the current sandbox landscape is Windows. Every platform mentioned in these comments like E2B, Daytona, Fly Sprites, Sandflare appears Linux-native. Makes sense for coding agents targeting Debian environments, but a real category exists to automate Windows-specific workflows: enterprise software, ERP systems, anything that runs only on Windows.
If anyone wants to run agents in Mac or Linux and need to access Windows for computer use, Dexbox could be helpful. [github.com/getdexbox/dexbox]
I launched an open source developer tool called Dexbox to run agent workloads that quickly provision and run Windows desktops. It's a CLI and MCP experience that's different from Freestyle, but slightly closer to our Windows-specific production infra, Nen. I like Freestyle's cool UI that shows off the unique technical approach and developer friendliness. Nen's a bit closer to that experience.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#175Ton of people have mentioned this but what you're doing with memory forking is pretty unique. Most sandboxes seem to just fork the filesytem and call it a day. Forking full VM memory mid-exec is taking it to another level entirely. Would be very interested to hear how the implementation looks under the hood, specifically how you handle dirty memory pages across forks without the pause ballooning.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#176The memory forking is really interesting. I wonder if copy-on-write at the VM level, O(1) with respect to machine size, won't scale cost with how many forks to take, but 320ms median seems good for the branch-and-explore pattern without reprovisioning every time. One gap I'm noticing in these comments and in the current sandbox landscape is Windows. Every platform mentioned in these comments like E2B, Daytona, Fly Sp…
Its actually almost O(1) with respect to fork count. We have some O(N) behaviors but I expect to be able to remove those in the next 6 months and get to full horizontal fork O(1) any VM any fork count.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#177[flagged]
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#178The observability point is real but honestly the loop detection problem is more about how you structure your agent than the sandbox. When I've had agents go rogue, the issue was always the outer loop logic, not visibility into the VM. What does your current loop controller look like?
[dead]
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#179Congrats on the launch!
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#180The memory forking is really interesting. I wonder if copy-on-write at the VM level, O(1) with respect to machine size, won't scale cost with how many forks to take, but 320ms median seems good for the branch-and-explore pattern without reprovisioning every time. One gap I'm noticing in these comments and in the current sandbox landscape is Windows. Every platform mentioned in these comments like E2B, Daytona, Fly Sp…
Its actually almost O(1) with respect to fork count. We have some O(N) behaviors but I expect to be able to remove those in the next 6 months and get to full horizontal fork O(1) any VM any fork count.
Ah, got it. Still impressive.