[flagged]
Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
131–140 of 147 posts
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#132Earlier quoted context omitted.
Is lakeFS an FS....? Zero mention of FUSE or a kernel module at all in the README.
The title says it's a new filesystem, you either need to use fuse or a kernel module.
I mean not really. There is a FUSE implementation, but you need an enterprise account https://docs.lakefs.io/v1.60/reference/mount/
I’m not seeing a kernel module anywhere..
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#133This is good and all, but it doesn't stop the agent from deleting you remote github branches, s3 data or potentially gdrive data. Are you able to set access read only? I'd never personally use something like this because I don't see what it offers over doing dev in a linux VM, and setting folders to read only with chattr. Most solutions can be engineered with standard Linux tools.
Exactly. Having just snapshots of db state isn't that useful, if running ai-slop queries has already triggered actions to external services (example: credit card issuer), warehouse processes (example: shipments, product lines...) , or similar.
There are of course some projects where it can be useful, assuming it works properly and that's not a given either when it's vibecoded.
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#134Git is already versioned, S3 support versioning and any file copied into the sandbox, is well a copy, so I am not sure what is the angle here. Other than that it looks cool!
Doesn't s3 now have versioning + POSIX mounts?
S3 Files is not POSIX compliant and doesn’t claim to be so. For example, atomic renames aren’t supported.
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#135I was trying to build an agent. None of the sandboxes out there had solved the filesystem problem. I want my agent to have a persistent storage, and that stays forever. Like a human with a computer. When the agent spins up again, it has access to the computer with the same files. I had to create my own setup using aws s3 filesystem and docker for this. Does Tilde solve for this?
Agent Sandboxes is the official k8s solution for this.
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#136[dead]
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#137Earlier quoted context omitted.
It's interesting to see this one launch (yes yet another sandbox.. I was getting worried we'd not seen one for a few days) SlicerVM (est. 2022) is already used for prime time, not "free as in beer" but has pretty reasonable individual plans that include all features. Shares the core code with actuated. (Creator of both speaking here) Feel free to take a look and see if gives you a little more than the others you ment…
What do you mean "not free as in beer"? Its not free as in anything? Sandboxes need to be open source, nothing else is acceptable.
Why should they be open source?
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#138Earlier quoted context omitted.
What do you mean "not free as in beer"? Its not free as in anything? Sandboxes need to be open source, nothing else is acceptable.
Why should they be open source?
Same reason linux or databases need to be open source. A sandbox is not a nice to have or a feature anymore, it is as fundamental building block to running any software. You cannot depend on closed source building blocks, not as closed source product and especially not as open source product.
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#139Very cool. Was this inspired by Cloudflare Artifacts? I'm working on a similar system as the backend for an upcoming agentic coding platform.
Re: Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
#140Earlier quoted context omitted.
I'm not having a debate because I'm quite ignorant of the subject. Just trying to learn from you: wouldn't recoverability and observability suffice instead of sandboxing, if such events are indeed rare? not necessarily for all usecases, but for most?
Yeah, I'm sure the reality is that a basic setup is fine for most casual development. The average user isn't concerned with security and we've basically normalized data breaches. If you have backups, use git, and manually approve Claude's access and actions, that's likely "good enough". The problem is you start getting comfortable and tired of your workflow getting interrupted when the agent needs more/repeated acces…
Makes a lot of sense. Thanks!