Skip to content

Latest commit

 

History

History
127 lines (93 loc) · 5.61 KB

File metadata and controls

127 lines (93 loc) · 5.61 KB

Mitos

Mitos

Isolated, forkable computers for your AI agents.
Millisecond microVM sandbox forking on Kubernetes.

Website  ·  Core repo  ·  Quickstart  ·  Discussions  ·  Discord

Mitos SDK: create a microVM sandbox, run code, and fork it into isolated parallel attempts

Try it in a few lines

import mitos

sb = mitos.create("python")              # Ready microVM sandbox (~27 ms warm-claim)
print(sb.exec("echo hello").stdout)      # hello

# Fork into independent siblings to try two approaches at once.
a, b = sb.fork(2)
a.exec("echo conservative > /workspace/plan.txt")
b.exec("echo aggressive  > /workspace/plan.txt")

sb.terminate()

Set MITOS_API_KEY from mitos.run. The base URL defaults to the hosted endpoint, so no Kubernetes required. The same code runs against a self-hosted cluster by setting MITOS_BASE_URL.

Why Mitos

  • ⑂ Live-fork a running VM. N-way copy-on-write fork of a live microVM: daughters share the parent's memory pages until they write, so each fork lands in a warm, ready environment. Branch one agent into many parallel attempts.
  • ⚡ ~27 ms warm-claim activate. Firecracker microVMs restore from a memory snapshot in the tens-of-milliseconds class. P50 ~27 ms on the bare-metal reference node, reproducible from a script in the repo.
  • ◎ Open-source, self-hostable, Kubernetes-native. As far as we know, the only runtime that does all three. Run it hosted, or on your own KVM cluster where your data never leaves your infrastructure.

Two ways to run

☁️ Hosted

A key and the SDK. No infrastructure to manage.

pip install mitos-run          # the import stays `import mitos`
export MITOS_API_KEY=sk-...

Get an API key

🖥️ Self-host

Any Kubernetes cluster with KVM nodes. Your data never leaves your infra. Bare metal (Hetzner + Talos) is a first-class target.

Self-host on Kubernetes

Project status

Release CI Go Report Card Go version License: Apache-2.0 GitHub stars

Fast, and we show our work

warm-claim activate ~27 ms P50

P50 ~27 ms warm-claim activate (snapshot load + fork-correctness handshake + guest-ready) on the bare-metal reference node, reproducible from bench/husk-activate-latency.sh. Full methodology in BENCHMARKS.md.

Explore

Contribute

We build in the open. Stars and issues genuinely help us prioritize.

⭐ Star the repo · Good first issues · Contributing · Security

Apache-2.0 · Mitos™ · trademarks.