Tarit – Self-host sandbox cloud and hypervisor for AI agents

Name: Tarit – Self-host sandbox cloud and hypervisor for AI agents
Availability: InStock
Author: mkagenius

by mkagenius·Jul 8, 2026·6 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidWizardryBig Brain

Live snapshots without pausing VMs—Firecracker can't do this.

Strengths

•Live snapshot of running guest without pause is genuine technical differentiation
•35ms p99 VM acquisition from warm pool with verifiable benchmarks

Weaknesses

•Only 4 stars indicates very early stage, unproven in production
•AI agent sandboxing is emerging category with undefined requirements

Post Description

We have built Tarit as a hypervisor built from ground up for running AI agent and RL environments. It is based on rust-vmm and can be used as a replacement for firecracker. Firecracker was built to serve a different need of primarily serverless compute and hence does not have primitives like live snapshots without pausing the VM operations.

We also provide a basic orchestrator that handles placement of the microVMs, creating clusters with HA, maintaining a warm pool of VMs, and takes care of setting up networking and monitoring.

Our benchmarks on a metal instance shows an acquire VM from pool and execute code p99 of 35ms which places it as one of the fastest VM based sandboxes you can get right now. You could also snapshot a small sandbox and resume in ~80ms.

You can easily self-host a multi-node cluster of this right now on your cloud with nested-virt enabled machines or better on bare metal by providing the docs to your coding agent.

Tarit - https://github.com/instavm/tarit

Quickstart - https://github.com/instavm/tarit/blob/main/orch/docs/QUICKST...