Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Freestyle – Sandboxes for Coding Agents

freestyle.sh

Post reply on HN
Print view View original

31–40 of 182 posts

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#31

Post by benswerd »

stocktech wrote: post #28

I built something like this at work using plain Docker images. Can you help me understand your value prop a little better? The memory forking seems like a cool technical achievement, but I don't understand how it benefits me as a user. If I'm delegating the whole thing to the AI anyway, I care more about deterministic builds so that the AI can tackle the problem.

So first MicroVM != Container, and container is not a secure isolation system. I would not run untrusted containers on your nodes without extra hardening.

The memory forking was originally invented because for AI App Builders and first response driven applications its extremely important that they are instant (difference between running bun dev and the dev server already being running).

However its much more generally applicable, Postgres is a great example of this. You can't fork the filesystem under postgres and get consistency. Same thing with a browser state, a weird server state, or anything that exists in memory. The memory forking gives a huge performance boost while snapshotting whats actually going on at one instant.

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#33

Post by indigodaddy »

benswerd wrote: post #29
stingraycharles wrote: post #25

I’m super interested since it seems like you have given everything a lot of thought and effort but I am not sure I understand it. When I’m thinking of sandboxes, I’m thinking of isolated execution environments. What does forking sandboxes bring me? What do your sandboxes in general bring me? Please take this in the best possible way: I’m missing a use case example that’s not abstract and/or small. What’s the end goal…

So isolation is correct. Forking a sandbox gives you multiple exact duplicates of isolated environments. When your coding agent has 10 ideas for what to do, to evaluate them correctly it needs to be able to evaluate them in isolation. If you're building a website testing agent and halfway down a website, with a form half filled out a session ongoing, etc and it realizes it wants to test 2 things in isolation, forking…

Yep I can see this especially when the agent is spinning up test servers/smokes and you don't want those conflicting. How do we reconcile all the potential different git hashes though, upstream I guess etc (this might be an easy answer and I'm not super proficient with git so forgive)

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#35

Post by moezd »

siva7 wrote: post #18

I have so many interesting problems on Ai, sandboxing isn't one of them. It's a pointless excercise yet disproportionately so many people love to to do this. Probably because sandboxing doesn't feel as magic as Agents itself and more like the old times of "traditional" software development.

Believe it or not, once you start working for a regulated industry, it is all you would ever think of. There, people don't care if you are vibing with the latest libraries and harnesses or if it's magic, they care that the entire deployment is in some equivalent of a Faraday cage. Plus, many people just don't appreciate it when their agents go rm -rf / on them.

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#36

Post by wsve »

stingraycharles wrote: post #25

I’m super interested since it seems like you have given everything a lot of thought and effort but I am not sure I understand it. When I’m thinking of sandboxes, I’m thinking of isolated execution environments. What does forking sandboxes bring me? What do your sandboxes in general bring me? Please take this in the best possible way: I’m missing a use case example that’s not abstract and/or small. What’s the end goal…

Agreed, the thing I'd be most interested in is the isolated execution environment you mentioned. Agents running autopilot are powerful. Agents running unsupervised on a machine with developer permissions and certificates where anything could influence the agent to act on an attacker's behalf is terrifying

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#37

Post by indigodaddy »

benswerd wrote: post #22
skybrian wrote: post #17

It doesn't seem very easy to calculate how much it would cost per month to keep a mostly-idle VM running (for example, with a personal web app). The $20/month plan from exe.dev seems more hobbyist-friendly for that. Maybe that's not the intended use, though?

We're not going after hobbyists. We're building the platform for companies like exe.dev to build on. Thats why its all usage based. That said, our $50 a month plan can be used as an individual for your coding agents, but I wouldn't recommend it.

Ooof, if you are the middleman platform then it's sure gonna get expensive for the end user

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#38

Post by benswerd »

indigodaddy wrote: post #33
benswerd wrote: post #29

Earlier quoted context omitted.

So isolation is correct. Forking a sandbox gives you multiple exact duplicates of isolated environments. When your coding agent has 10 ideas for what to do, to evaluate them correctly it needs to be able to evaluate them in isolation. If you're building a website testing agent and halfway down a website, with a form half filled out a session ongoing, etc and it realizes it wants to test 2 things in isolation, forking…

Yep I can see this especially when the agent is spinning up test servers/smokes and you don't want those conflicting. How do we reconcile all the potential different git hashes though, upstream I guess etc (this might be an easy answer and I'm not super proficient with git so forgive)

So we recommend branch per fork, merge what you like.

You have to change the branch on each fork individually currently and thats unlikely to change in the short term due to the complexity of git internals, but its not that hard to do yourself `git checkout -b fork-{whateverDiscriminator}`

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#39

Post by benswerd »

wsve wrote: post #36
stingraycharles wrote: post #25

I’m super interested since it seems like you have given everything a lot of thought and effort but I am not sure I understand it. When I’m thinking of sandboxes, I’m thinking of isolated execution environments. What does forking sandboxes bring me? What do your sandboxes in general bring me? Please take this in the best possible way: I’m missing a use case example that’s not abstract and/or small. What’s the end goal…

Agreed, the thing I'd be most interested in is the isolated execution environment you mentioned. Agents running autopilot are powerful. Agents running unsupervised on a machine with developer permissions and certificates where anything could influence the agent to act on an attacker's behalf is terrifying

I recommend running the agent harness outside of the computer. The mental model I like to use is the computer is a tool the agent is using, and anything in the computer is untrusted.

Re: Launch HN: Freestyle – Sandboxes for Coding Agents

#40

Post by benswerd »

rsyring wrote: post #12
_jayhack_ wrote: post #4

Would love to understand how you compare to other providers like Modal, Daytona, Blaxel, E2B and Vercel. I think most other agent builders will have the same question. Can you provide a feature/performance comparison matrix to make this easier?

I'd also be interested in a comparison with exe.dev which I'm currently using.

Exe.dev is a individual developer oriented service. Freestyle is more oriented at platforms building the next exe.dev.

Thats why our pricing is usage based and we have a much larger API surface.

Post reply on HN