FUSE is All You Need – Giving agents access to anything via filesystems
118 points
11 hours ago
| 12 comments
| jakobemmerling.de
| HN
heavyset_go
10 hours ago
[-]
IMO, for real file systems, just give a view via cgroups/namespaces.

Implementing a database abstraction as a file system for an LLM feels like an extra layer of indirection for indirection's sake: just have the LLM write some views/queries/stored procs and give it sane access permissions.

LLMs are smart enough to use databases, email, etc without needing a FUSE layer to do so, and permissions/views/etc will keep it from doing or seeing stuff it shouldn't. You'll be keeping access and permissions where they belong, and not in a FUSE layer, and you won't have to maintain a weird abstraction that's annoying/hampered with licensing issues if you want to deploy it cross platform.

Also, your simplified FUSE abstraction will not map accurately to the state of the world unless you're really comprehensive with your implementation, and at that point, you might as well be interacting directly in order to handle that state accurately.

reply
jakobem
10 hours ago
[-]
Agree that to far fetched mappings to files don’t really make sense. The email example is more illustrative then real world inspired, thought it might be good to show how flexible the approach is.

I think there is a gap between “real file systems” and “non file things in a database” where mapping your application representation of things to a filesystem is useful. Basically all those platforms that let users upload files for different purposes and work with them (ex Google Drive, notion, etc). In those cases representing files to an agent via a filesystem is the more intuitive and powerful interface compared to some home grown tools that the model never saw during training.

reply
eru
6 hours ago
[-]
See my own https://github.com/matthiasgoergens/git-snap-fs which lets you expose all branches and all tags and all commits and all everything in a git repository as a static directory tree. No need to git checkout anything: everything is already checked out.
reply
ximeng
9 hours ago
[-]
LLMs can handle Google drive perfectly well with a service account, including the Google drive specific quirks through the API. It could be helpful to expose via a file system rather than a custom API if you wanted a different interface than Google already provides, but this wouldn’t be driven by the limitations of the LLM.
reply
jakobem
9 hours ago
[-]
In terms of ergonomics, I’d say a filesystem is more intuitive for an agent than the Google Drive API even if it can handle both. Hard to argue without building an eval set and evaluating both, though.
reply
ximeng
8 hours ago
[-]
I’ve been doing this recently and for the basics agents had no problem with the API apart from the weird behaviour of shared drives needing a special flag to handle them. This could probably be mapped to a file system in a way that wouldn’t trip up an agent, but at the expense of losing the Google drive specific functionality. A trade off, not much better or worse per se, but with the added complexity of the FUSE layer.
reply
outofpaper
9 hours ago
[-]
The less juggling of concepts thr more effective any problem solver cam be.
reply
efitz
5 hours ago
[-]
In my experience LLMs excel at SQL.
reply
_pdp_
7 hours ago
[-]
We have also attempted to implement exactly this but it turned out to be really bad architecture.

The file system as an abstraction is actually not that good at all beyond the basic use-cases. Imagine you need to find an email. If you grep (via fuse) you will end up opening lots of files which will result in fetches to some API and it will be slow. You can optimise this and caching works after first fetch but the method is slow. The alternative is to leverage the existing API which will be million times faster. Now you could also create some kind of special file via fuse that acts like a search but it is weird and I don't think the models will do well with something so obscure.

We went as much as implementing this idea in rust to really test it out and ultimately it was ditched because, well it sucks.

reply
AdieuToLogic
5 hours ago
[-]
> The file system as an abstraction is actually not that good at all beyond the basic use-cases. Imagine you need to find an email.

Unrelated to FUSE and MCP[1] agents, this scenario reminded me of using nmh[0] as an email client. One of the biggest reasons why nmh[0] is appealing is to script email handling, such as being able to use awk/find/grep/sed and friends.

0 - https://www.nongnu.org/nmh/

1 - https://en.wikipedia.org/wiki/Model_Context_Protocol

reply
skissane
6 hours ago
[-]
> If you grep (via fuse) you will end up opening lots of files which will result in fetches to some API and it will be slow.

This is a limitation of the POSIX filesystem interface. If there were a grep() system call, it could delegate searches to the filesystem, which could use full text indices, run them on a remote server, etc

reply
trollbridge
5 hours ago
[-]
Or maybe a file system is best used to store files and not be a general database manager.
reply
nextaccountic
2 hours ago
[-]
Yep, but unfortunately this is the interface FUSE will expose
reply
tombert
8 hours ago
[-]
I've been getting into FUSE a bit lately, as I stole an idea that a friend had of how to add CoW features to an existing non-CoW filesystem, so I've been on/off been hacking on a FUSE driver for ext4 to do that.

To learn FUSE, however, I started just making everything into filesystems that I could mount. I wrote a FUSE driver for Cassandra, I wrote a FUSE driver for CouchDB, I wrote a FUSE driver for a thing that just wrote JSON files with Base64 encoding.

None of these performed very well and I'm sort of embarrassed at how terrible the code is hence why I haven't published them (and they were also just learning projects), but I did find FUSE to be extremely fun and easy to write against. I encourage everyone to play with it.

reply
eru
6 hours ago
[-]
Writing a fuse frontend for git is particularly rewarding: git is already more or less organised like a file system internally.
reply
tombert
5 hours ago
[-]
I believe that.

FUSE makes me think that the Plan 9 people were on to something. Filesystems actually can be a really nice abstraction; sort of surreal that I could make an application so accessible that I could seriously have it directly linked with Vim or something.

I feel like building a FUSE driver would be a pretty interesting way to provide a "library" for a service I write. I have no idea how I'd pitch this to a boss to pay me to do it, but pretending that I could, I could see it being pretty interesting to do a message broker or something that worked entirely by "writing a file to a folder". That way you could easily use that broker from basically anything that has file IO, even something like bash.

I always have a dozen projects going on concurrently, so maybe I should add that one to the queue.

reply
eru
5 hours ago
[-]
See https://github.com/matthiasgoergens/git-snap-fs for my example of read-only access to git via fuse.

I built the original version in Python for a job years ago. But the version above is almost entirely vibe-coded in Rust in a lazy afternoon for fun.

However, I disagree that the filesystem is the right abstraction in general. It works for git, because git is essentially structured like a filesystem already.

More generally, filesystems are roughly equivalent to hierarchical databases, or at most graph databases. And while you can make that work, many collections of data are actually better organised and accessed by other means. See https://www.seas.upenn.edu/~zives/03f/cis550/codd.pdf for an particularly interesting and useful model that has found widespread application and success.

reply
tombert
5 hours ago
[-]
Yeah I'm not saying that they're necessarily great in general, just that there are certain applications that map pretty well, and for those it's a pretty cool abstraction because it allows virtually anything to interface with it.

Also, looks like my message queue idea has already been done: https://github.com/pehrs/kafkafs

No new ideas under the sun I suppose.

reply
fleshmonad
9 hours ago
[-]
Welcome back Plan9
reply
Imustaskforhelp
6 hours ago
[-]
It never left :p (I think that there are still active forks of Plan9 and Plan9 itself has definitely influenced some linux features or so I have heard)
reply
fleshmonad
5 hours ago
[-]
Yes there is the great 9front and the useful plan9port. I run 9front on an old thinkpad, but I plan on doing a little more with it, having a dedicated CPU server, storage server etc will be the next step
reply
rescrv
5 hours ago
[-]
For my LLM/agents framework, I went with a virtual filesystem abstraction and implemented helpers for mounting and permissioning the virtual file systems: https://github.com/rescrv/claudius/blob/main/src/agent.rs#L1...
reply
eru
6 hours ago
[-]
See my own https://github.com/matthiasgoergens/git-snap-fs which lets you expose all branches and all tags and all commits and all everything in a git repository as a static directory tree. No need to git checkout anything: everything is already checked out.
reply
disdi89
3 hours ago
[-]
Do you know how does it impact the RAG usecase? Do I not need those vector databases anymore if I instead use this FUSE layer?
reply
mickael-kerjean
9 hours ago
[-]
> My prediction is that one of the many sandbox providers will come up with a nice API on top of this that lets you do something like ... No worrying about FUSE, the sandbox, where things are executed, etc. This will be a huge differentiator and make virtual filesystems easily accessible to everyone.

I've done exactly that with Filestash [1] using its virtual filesystem plugin [2], which exposes arbitrary systems as a filesystem. It turns out the filesystem abstraction works extremely well even for systems that are not filesystems at all. There are connector for literally every possible storage (SFTP, S3, GDrive, Dropbox, FTP, Sharepoint, GCP, Azure Cloud, IPFS....), but also things like MySQL and Postgres (where the first level folder represent the list of databases, the second level is tables that belong to a database, and each row is represented as a form file generated from the schema), LDAP (where tree nodes are represented as folders and leaf are form files), ....

The whole filesystem is available to agents via MCP [3] and has been published to the OpenAI marketplace since around Christmas, currently pending review.

ref:

[1]: https://github.com/mickael-kerjean/filestash

[2]: https://www.filestash.app/docs/guide/virtual-filesystem.html

[3]: https://www.filestash.app/docs/guide/mcp-gateway.html https://github.com/mickael-kerjean/filestash/tree/master/ser...

reply
ohnoesjmr
8 hours ago
[-]
Why not just MCP? Feels like easier to implement and doesn't need a filesystem/root/admin perms?
reply
dkdcio
8 hours ago
[-]
a few reasons:

- agents tend to need (already have) a filesystem anyway to be useful (not technically required but generally true, they’re already running somewhere with a filesystem)

- LLMs have a ton of CLI/filesystem stuff in their training data, while MCP is still pretty new (FUSE is old and boring)

- MCP tends to bloat context (not necessarily true but generally true)

UNIX philosophy is really compelling (moreso than MCP being bad). if you can turn your context into files, agents likely “just work” for your use case

reply
mbreese
4 hours ago
[-]
I’m sympathetic to this idea, but there is no LLM training data for how to access random data like this using a filesystem through a FUSE interface.

Yes, it should be able to generically use a filesystem, but there has to be a better way to find an email than greping through each email as a file.

So, I see merit in the idea in theory, I’m just skeptical in practice.

reply
everlier
10 hours ago
[-]
I've implemented agentic framework exactly like this for my current employer.

It opens up absolutely bonkers capabilities.

reply
Eikon
9 hours ago
[-]
For ZeroFS [0], I went an alternate route with NFS/9P. I am surprised that it’s not more common as this approach has various advantages [1] while being much more workable than fuse.

[0] https://github.com/Barre/ZeroFS

[1] https://github.com/Barre/ZeroFS?tab=readme-ov-file#why-nfs-a...

reply
jakobem
9 hours ago
[-]
Interesting! The network first point makes a lot of sense, especially bc you will most likely not access your actual datastore within the process running in the sandbox and instead just call some server that handles db access, access control etc.
reply
moonlet
10 hours ago
[-]
I am so sick of the ‘sandboxed’ AI-infra meme. A container is not a sandbox. A chroot is not a sandbox. A VM is also not a sandbox. A filesystem is also also not a sandbox. You can sandbox an application, you can run an application in a secure context, but this is not a secure context the author is describing, firstly, and secondly they haven’t described any techniques for sandboxing unless that part of the page didn’t load for me somehow.
reply
jakobem
10 hours ago
[-]
Didn’t mean to say this is a sandbox, it certainly isn’t, this is just an illustration on how to bridge the gap and make things available in a file system from the source of truth of your application.

There is tons of more complexity to sandboxing, I agree!

reply
moonlet
6 hours ago
[-]
No worries! And I definitely appreciate you taking time to write up your work, it’s a good blog.
reply
Imustaskforhelp
6 hours ago
[-]
I recently had a question about what AI sandboxes use and I think Modal uses gvisor under the hood and I think others use firecracker/generally favour it as well

Firecracker kind of ends up being in the VM categories and I would place gvisor in a similar category too under the VM

So in my opinion, VM's are sandboxes.

Of course there is also libriscv https://github.com/libriscv/libriscv which is a sandbox (The fastest RISC-V sandbox)

There is also https://github.com/Zouuup/landrun Run any Linux process in a secure, unprivileged sandbox using Landlock. Think firejail, but lightweight, user-friendly, and baked into the kernel.

Your mileage may vary but I consider firecracker to be the AI sandbox usually. Othertimes it can be that they abstract on a cloud provider and open up servers in that or similar (I feel E2B does this on top of gcp)

reply
eyberg
4 hours ago
[-]
A lot of these "ai sandbox" conversations target code that is already running in a public cloud. Running firecracker doesn't give you magical isolation properties vs running an application in ec2 - it's the same boundary. If you're trying to compare to running multi-tenant workloads in containers on the same vm vs different tenants on different vms - sure that's an improvement but no one said you had to run containers to begin with.

Furthermore, running lots of random 3rd party programs in the same instance, be it a container, or an ec2 vm, or a firecracker vm all have the same issues - it is inherently totally unsafe. If you want to "sandbox" something you need to detail what exactly you are wanting to isolate.

A lot of people might suggest not being able to write to the filesystem, read env vars, or talk over the network but these are table stakes for a lot of the workloads that people want to "isolate" to begin with.

So not only is there this incorrect view that you are isolating anything at all, but I'm not convinced that the most important things, like being able to run arbitrary 3rd party programs, is even being considered.

reply
tptacek
9 hours ago
[-]
Wait, can you provide the positive definition for "sandbox" you're relying on here?
reply
moonlet
6 hours ago
[-]
To me ‘a sandbox’ is a secured context, which is specific to whatever is in it. It is not a generic thing unless we are literally referring to a real-world box with sand in it, and I’ve kinda hit the breaking point with the term in tech. ‘A sandboxed application’ to me is an instrumented and controlled deployment of an application that can only make the sys/network/ipc calls the deployer expects and appreciates, which are then themselves filtered and monitored. A sandboxed deployment of an application? Sure. That’s a thing to me. But each application needs different privileges and does different things. Sandboxing an application may involve lots of different technologies. Eg the way I think about it, things like seccomp, apparmor, et al also aren’t themselves ‘sandboxes’, they’re enforcement mechanisms which rely on knowing and configuring them to monitor and enforce what the app should and shouldn’t do. A lot of things that assist with sandboxing may also be combined in different ways to get to a more secure environment, in which the app is sandboxed.
reply
akerl_
6 hours ago
[-]
You may just be using a personalized definition of that word, that differs from what it means.

https://en.wikipedia.org/wiki/Sandbox_(computer_security)

Notably, a sandbox exists to separate one thing from other things. Limiting/filtering/monitoring what the sandboxes thing can do are often components of that, but the underlying premise is about separation.

Containers, VMs, etc. are 100% examples of sandboxing based on the actual industry definition of the term.

reply
moonlet
5 hours ago
[-]
I’m saying I don’t think sandbox is a noun, I think it’s a verb. I also don’t get why this is such an issue to you? A container simply is not a sandbox by itself. The collection of technologies that can sandbox can be used to sandbox a container, or an app running in a container, or whatever you want. A door lock isn’t security, a door lock is used to lock your door, which gives you part of a security strategy. Same principle.
reply
akerl_
5 hours ago
[-]
> I’m saying I don’t think sandbox is a noun, I think it’s a verb.

You are incorrect.

reply
moonlet
5 hours ago
[-]
What background or context do you have that you base this claim on?
reply
tptacek
5 hours ago
[-]
He's obviously right about the noun/verb thing. You can just look this up on Google Scholar. I think you're sort of broadly wrong about how fussy the definition of a "sandbox" is, but you're at least saying something coherent there, even if it's an idiosyncratic definition.
reply
akerl_
5 hours ago
[-]
I already gave you a link above with a definition of sandbox, the noun, and a list of example technologies that it applies to.

If you’re going to get fired up about people you feel are misusing this term, and then ignore citations about its actual definition, I think the ball’s in your court to back up your claim.

reply
moonlet
4 hours ago
[-]
I mean… I’m flattered you think I’m making some kind of statement here but there is no claim. I literally stated an opinion I hold in a comment on HN, I didn’t write a you a thesis. Followed by explaining further the details of that opinion.

I’ve asked what background leads to your conclusion, because if you have eg written some sandboxing tooling, I’d be curious to give it a look. Always up to learn things, and I am more than a little baffled by how upset the comments I’m replying to here sound. You’ve linked me to Wikipedia, and another commenter asserts I can ‘just look it up on google scholar’. That seems pretty dismissive and reductive overall.

reply
antonvs
1 hour ago
[-]
Let me chatgpt that for you - from https://chatgpt.com/share/69649d10-74b4-8001-9a66-71c7258aa3... :

Noun usage is standard across:

- Operating system security (e.g., Linux namespaces, seccomp, chroot-based sandboxes)

- Browser security (Chrome, Firefox, WebKit sandboxes)

- Mobile platforms (Android app sandbox, iOS sandbox)

- Malware analysis (“run the sample in a sandbox”)

- Cloud and container security

The noun form appears routinely in:

- Vendor documentation (Google, Apple, Microsoft)

- Academic security literature

- Industry standards and guidance (e.g., NIST documents, browser security models)

reply
eyberg
4 hours ago
[-]
No they are not. The "industry" totally disagrees with this statement as well.
reply
lagniappe
9 hours ago
[-]
Please brother may i have some pledge unveil
reply
ape4
4 hours ago
[-]
By your definition, a physical child's sandbox isn't a sandbox.
reply