Viewing profile — dorianzheng

i built a similar project named boxlite (embeddable micro-VM) and agentlite (agent in boxlite). i like your idea

got it, will definitely check it out do you have some performance number of lakeFS in your mind

seems cool to integrate with https://github.com/boxlite-ai/boxlite and https://github.com/boxlite-ai/agentlite

is it possible to run it inside local micro-VM, such as boxlite?

how's the performance compare to boxlite?

it would be cool if we can integrate it with the local micro-VM https://github.com/boxlite-ai/boxlite

any chance i can run local micro-VM such as boxlite with this?

not yet for memory, just persistent storage snapshotting/forking right now

Hi HN. I'm Dorian, founder of Polygala. We are building a micro-VM runtime for all kinds of use case including embedded like SQLite, local deployment like MySQL and cloud deploymen…

+1. That’s basically what I want too: npx skills but for Python. For now BoxLite is the isolation/runtime layer; the “skills registry + one-liner runner” is a thin wrapper we can a…

I think you basically answered the entire question 1. Our fundamental assumption is: anything that hands control to an agent/skill is potentially compromised (especially if it touc…

I've been thinking about AI agents wrong. We keep treating them as this special thing that needs special infrastructure. But what if agent skills are just... functions you compose?…

The problem: AI agents are most useful when they have freedom—freedom to write code, install packages, run scripts, explore solutions. But that freedom is dangerous. One hallucinat…

I gotta say StarRocks is not only a MPP database. It's also a distributed SQL engine for data lake analytics. https://github.com/StarRocks/starrocks/pull/2225