-
The holy grail microVM for me is one that can properly share a GPU across VMs, similar to what you can do with containers.
Shout out to https://smolmachines.com/ for supporting Vulkan over virtio-gpu/Venus. Currently the best implementation I'm aware. Unfortunately my use case is running a full desktop inside the VM, and streaming it out over something like Sunshine/Moonlight. For this you need GPU rendering and video encoding. Venus rendering works, but you have to pass the frames back and forth between the host and the VM multiple times which is inefficient. Also Venus doesn't support video encode as far as I can tell.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
mitos
Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running VM into N copies, and persist durable, versioned workspaces. Self-hostable, declarative CRDs.
Interesting, I have recently started working on https://github.com/mitos-run/mitos which is similar and fully open source. If someone's interested I'd love to learn about any feedback on this!
Didn't mean to highjack for self advertisement. As the topic matches, the open source nature of my project might be appealing to some here.
-
Not so subtle plug from yet another sandbox provider, https://instavm.io :
Apart from the above features.
1. We support more than 32GB disk (as a detachable device, ideal for agentic memory)
2. We provide egress control
3. We provide vault for secret injection (to counter prompt injection)
4. Snapshot / forking.
Everything supported in APIs and CLI for agents.
Can be used via - npx skills add instavm/skills
-
Then there's also the option to use libkrun to run local sandboxes on your own computer. That doesn't scratch the itch for hosted services, but works if your goal is to run agents inside isolated environments for your own work.
I've been working on some open-core stuff[1] to coordinate sandboxes, and we're making changes so have a library that lets people coordinate any number of remote or local sandboxes using any provider, kinda like how the Docker CLI works for managing containers. Flue[2] is another player in this space, and is more of a pure framework, while we're building it as an interactive product for using sandboxed agents and workflows.
[1]: https://github.com/gofixpoint/amika/blob/main/ROADMAP.md -
I’ve been working with AgentCore that uses the same MicroVMs. They are capable in many ways but for coding agents that load a big got repo they get bloated quickly with the git repo.
I’m building this google3 style mounting to address this.
https://github.com/mohsen1/git-lazy-mount
Still work in progress but for now I am seeing promising results
-
sandboxd
Open-source, self-hosted AI app builder — an agent builds real apps in isolated sandboxes on your own server, each live at a preview URL. Self-host in one command. MIT.
There are plenty of OSS solutions available for your needs. Do you need real isolation, or is Docker hardening sufficient? If hardening is suddicient check out https://github.com/tastyeffectco/sandboxd/ whcih i'm using internaly for so many use cases
-
agent-sandbox
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
We’re adopting agent-sandbox (https://agent-sandbox.sigs.k8s.io/) as we already run most if our stuff in kubernetes and it’s been working very well, the only downside being it’s a moving target as it’s still essentially in development.
-
microvm-fun
A sample repo showing Kubernetes running on a fleet of AWS Lambda MicroVMs, and the ability to SSH into MicroVMs
I've been kicking the tyres on this. I managed to get Kubernetes (k3s) running across a cluster of MicroVMs. Useful? No. Funny? To me, yes. https://github.com/aidansteele/microvm-fun
Related posts
-
TTFT is not TTFB: what 45 AI APIs measured from 4 regions actually show
-
Tenant Cost Attribution Explained — 3 Fallback Models Behind One Chatbot API
-
Per-Tenant Media Scheduling Explained: Node.js LLM JSON Schema for Ticket Tags
-
Speech-to-Text API 429 Triage: Backoff, Queue, and Batch Transcription
-
Marketplace Moderation Triage: API Gateway Caching, Batch Cost, Node.js, US/EU