🏖️ How to run your own local sandboxes (give this to your agent):
A spare Linux box can run your coding agent's sandboxes with each one getting its own microVM and private env vars
Mine's running on a Framework, completely replaced Vercel Sandbox for my demos
- @microsandbox runs each sandbox as a VM with its own kernel instead of a container
- the VM gets a placeholder key; the proxy swaps in the real one only on calls to that host and keys expire with the sandbox
- a firewall keeps it off the host's own services, my home network and tailnet; only the public internet
- each one gets 2 CPUs and 4 GB, up to 10 run at once and stops after idle for 30 minutes
prompt in reply
one line install:
curl -fsSL install.microsandbox.dev | sh
microsandbox retweeted
.@microsandbox now 5th on DAX bench.
we've been investing a lot into performance of our runtime over the past couple months, and it shows. some of those changes got rolled out to the cloud only recently (still private beta).
trailing on TTI bench, with lots of improvements in our backlog. expect to see more of those wins as we roll out more exciting features and improvements.
microsandbox retweeted
if you want this too but don't have lovable-level time and money, @microsandbox is the open-source alternative that gives you this and more.
O_DIRECT is shipped for disk and memory is next.
microsandbox retweeted
Silo: a native macOS/Linux app for sandboxes on your machine or remote ones. Powered by MicroSandbox.
Meant for letting agents run wild in isolated Linux VMs.
Open a workspace in your editor or terminal, forward ports, keep secrets on the host, scope GitHub access per sandbox, snapshot the environment.
github.com/0xpolarzero/silo
microsandbox retweeted
Some progress: Secret injection now working. The agent doesn't know and see the secret, but gets injected at network level by @microsandbox
microsandbox retweeted
okay Jev is an INSANE unlock, I just gave Mario a multiverse.
built "Mario Never Dies" with @typesafeai's Jev + microsandbox
Jev picks every move and every time Mario dies, we fork the entire VM into 4 timelines and try again.
whichever Mario survives becomes canon. it is like the others never happened.
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
microsandbox retweeted
i got jev + an llm playing doom, with a twist: try several futures, then keep playing from the best outcome.
jev picks the moves. a custom harness uses @microsandbox to run attempts in parallel from the same checkpoint. the llm reviews what happened and guides what to try next.
not enough? it rewinds to an earlier checkpoint and tries another path.
microsandbox retweeted
network rate limiting for microsandbox just shipped.
limit ingress or egress by bandwidth or packet rate or for one-time bursts.
by default, all sandbox network traffic is un-throttled.
microsandbox retweeted
Released the sandbox part of my Software Factory @microsandbox in Nomad! github.com/jamescorbett/noma… just as easy as any other job.
Smithers now has a preferred sandbox provider @microsandbox. It's fully open source allowing us in future releases to easily build smithers specific integrations
microsandbox retweeted
microsandbox now has a "what’s wrong?" and an "undo the update" command.
- msb doctor for diagnostics.
- msb self downgrade for safe rollbacks.
microsandbox retweeted
I ended up building a light REST API around @microsandbox because it has everything I need. I can now easily run it as a side car to any web apps that need a sandbox in my docker compose. Simple.
github.com/mark3labs/msbd
microsandbox retweeted
I’ve created internal tooling for sandboxing all agent workflows in just 2 days, and it all just works flawlessly all the time. I‘d never have thought it could be **that** easy.
microsandbox retweeted
native SSH support now in [email protected]. 🍻
previously, you'd run sshd inside the sandbox and expose a port. well, no more. point your existing ssh/sftp clients straight at it.
available in all SDKs and CLI today. 🪅
microsandbox retweeted
we built the most secure way to play doom 💀
it's friday and what better way to play doom than in your sandbox 😂
msb run ghcr.io/superradcompany/term…

























