Why not use KVM?

Having used this for our research, I highly recommend Rtrvr.

Maybe we should write an agent that writes an agent that writes an agent...

That seems like a naive take. If any of your local VMs are internet connected and are compromised, side channel attacks could be used to exfiltrate data from other VMs or the host.

Then why only apply to VMs, why not apps?

Why not use VMs from AWS (EC2) or GCP? E2b is built on top of GCP anyway.

Startups would build on big tech, so are likely to add their margins. Have you looked into (bulk) discounts from GCP/AWS?

> It does take 1-5 seconds to boot the environment (firecracker vms).

I'd say 1-5 secs is fast. Curious to know what use cases require faster boot up, and today suffer from this latency?

When your agent performs 20 tasks saving seconds here and there becomes a very big deal. I cannot even begin to describe how much time we've spent on optimising code paths to make the overall execution fast.

Last week I was on a call with a customer. They where running OpenAI side-by-side with our solution. I was pleased that we managed to fulfil the request under a minute while OpenAI took 4.5 minutes.

The LLM is not the biggest contributor to latency in my opinion.

Thanks! While I agree with you on "saving seconds" and overall latency argument, according to my understanding, most agentic use cases are asynchronous and VM boot up time may just be a tiny fraction of overall task execution time (e.g., deep research and similar long running tasks in the background).

Have you tried e2b or Daytona fast start vms?

That's what the author is claiming. Practically, VM-level strong fault isolation cannot be achieved without isolation support from the hardware aka virtualization.

Hardware without something like SR-IOV is straight up going to be unshareable for the foreseeable future; things like ring buffers would need a whole bunch of coordination between kernels to share. SR-IOV (or equivalent) makes it workable, an IOMMU (or equivalent) then provides isolation.

You could have a “nanokernel” which owns the ring buffers and the other kernels act as its clients… or for a “primary kernel” which owns the ring buffers and exposes an API the other kernels could call. If different devices have different ring buffers, the “primary kernel” could be different for each one.

That sounds like the Exokernel project. Notably different from a "multikernel"/"replicated kernel" design.

Why? stopping LLM crawlers is a need now. We've seen more capable people working for undergrad dropouts.

> Meta seems like one of the few large tech companies where if the whole company vanished, the world would be purely a better place.

100%