⚡ fast, secure microvms for untrusted workloads - agents sandboxes, ci/cd, etc. · self-host | byoc | on-prem · YC F26 → github.com/microsandbox/micr…
Joined April 2025
- Tweets 71
- Following 7
- Followers 465
- Likes 95
11 Photos and videos
Pinned Tweet
Apr 17
introducing microsandbox.
fast, local sandboxes built for agents that ship. 🚢
every agent needs to run code somewhere. we made that somewhere, and it shouldn’t always be the cloud.
23
42
266
44,767
Jun 6
🧵microsandbox 0.5.5 is out, and we're grinning. 🎉
you can now stream live per-sandbox metrics to any OTLP backend, offline import images from docker, amongst other things we're excited about.
👇
1
1
16
1,464
Jun 6
wondering what else shipped this week? checkout out this week's changelog: docs.microsandbox.dev/change…
1
2
113
Jun 6
these all builds up to something big and exciting ... local-first, but fully cloud compatible sandboxes, just as we promised! can't wait to share all the details sooon. 😃
we're gradually inviting folks to our private beta. interested? join the waitlist: microsandbox.dev/#waitlist
2
99
Jun 1
reminder: if your user can run docker, your user is root.
microsandbox has no daemon and runs rootless. nothing on your host is sitting there doing root favors.
you get a hardware-isolated microVM, full stop.
2
7
595
May 30
⚡ Microsandbox just leveled up (v0.5.x)
🔐 Native SSH & SFTP, no sshd needed
📂 New file commands (copy, mkdir, rm)
🛡️ Hardened mounts env-backed secrets
💾 Configurable OCI upper sizes
Faster networking. Tighter security. Same blazing-fast sandboxes. 🚀
docs.microsandbox.dev/change…
1
2
9
536
microsandbox retweeted
May 30
native SSH support now in microsandbox@0.5. 🍻
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. 🪅
1
6
16
1,284
May 27
in microsandbox, the real API key never enters the sandbox. the guest only ever sees a deterministic placeholder.
policy at the network boundary decides whether each outbound request gets the real value, gets blocked, gets passed through inert, or terminates the runtime.
why secret injection alone isn't enough for agents:
2
171
死ぬほど便利でビックリしてる。
superradcompany/microsandbox: 🧱 secure, local and programmable sandboxes for AI agents github.com/superradcompany/m… miteru
CI 作るのに良さそう。
10
94
24,900
May 19
remember when we said we made our filesystem faster?
we did more work on it and it got even faster.
faster than docker!
2
8
1,001
May 18
--help is a bad discovery mechanism and we've all just agreed to pretend it isn't
it's 2026 and to learn one CLI you --help, pick a subcommand, --help again, go deeper, --help again.
what is this, a corn maze?
microsandbox has --tree. it prints the whole command surface at once, at any depth. msb --tree, msb create --tree, msb image pull --tree.
the whole tool, instantly greppable. why is this not standard.
1
4
26
5,865
microsandbox retweeted
May 15
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…
1
4
7
775
microsandbox retweeted
May 13
do give @microsandbox a try!
spins up in ~300-400ms for ubuntu images. benchmarks should be up soon, but can walk through it private with you already.
to give an idea, here's a benchmark a c3-192-metal on GCP. goes from 0-200 parallel sandboxes on a single node in ~1.5s for p99, and 1k sandboxes in ~23s (btw, no warm pooling yet) lots of performance improvements we've got lined up.
it's an SDK you can build on, with an option to run on your infra soon. happy to walk you through the deets over a call.
2
7
821
microsandbox retweeted
May 11
Agents file sandboxes are all in the range in 2026 🤖🗃️
This is a nifty reference implementation by @itsclelia showing you how to run your agent over a collection of docs (PDFs, images, Office) with full access to a secure, local-first sandbox.
✅ Uses LiteParse for extremely fast parsing of all these docs ⚡️
✅ Uses agent harness native bash commands available to the sandbox (@microsandbox ) to do retrieval
Check it out!
Reference repo: github.com/run-llama/sandbox…
LiteParse: github.com/run-llama/litepar…
May 11
Ever wished your agent could read PDFs, images, and Office documents as easily as plain text?
Or combine the safety of a secure sandbox with the full power of Bash access?
We built exactly that.
Meet 𝘀𝗮𝗻𝗱𝗯𝗼𝘅𝗲𝗱-𝗹𝗶𝘁, a Rust 🦀 CLI agent that combines:
- LiteParse, our lightning-fast local parser for PDFs, images, Office files, and more
- A secure sandbox powered by @microsandbox
- Full filesystem mounting, so your agent can safely interact with local files inside the sandbox
Mount your local workspace, give the agent shell access, and let it do its magic 🪄
👩💻 GitHub: github.com/run-llama/sandbox…
📚 Learn more about LiteParse: developers.llamaindex.ai/lit…–
9
14
89
10,705
May 11
agents getting real machines is the whole point.
@llama_index this is lit 😉🦀
May 11
Ever wished your agent could read PDFs, images, and Office documents as easily as plain text?
Or combine the safety of a secure sandbox with the full power of Bash access?
We built exactly that.
Meet 𝘀𝗮𝗻𝗱𝗯𝗼𝘅𝗲𝗱-𝗹𝗶𝘁, a Rust 🦀 CLI agent that combines:
- LiteParse, our lightning-fast local parser for PDFs, images, Office files, and more
- A secure sandbox powered by @microsandbox
- Full filesystem mounting, so your agent can safely interact with local files inside the sandbox
Mount your local workspace, give the agent shell access, and let it do its magic 🪄
👩💻 GitHub: github.com/run-llama/sandbox…
📚 Learn more about LiteParse: developers.llamaindex.ai/lit…–
182