Tarit
Self-host sandbox cloud and hypervisor for AI agents
Details
- External ID
- 48829512
- Source
- HN
- Company
- —
- Product
- Tarit
- Website domain
- github.com
- Launched
- July 8, 2026
- Cohort
- —
- Upvotes
- 6
- Upvotes percentile
- 0.2873357228195938
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
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/taritQuickstart - https://github.com/instavm/tarit/blob/main/orch/docs/QUICKST...
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- self-hosted sandbox and hypervisor for ai agents
- Manually corrected
- False
Could you build this?
No Developing a custom hypervisor and virtualization cloud for sandboxed workloads requires deep systems programming with rust-vmm, KVM, memory management, and live snapshotting.
What it would actually take: The architecture involves building custom Virtual Machine Monitors (VMM) in Rust using `rust-vmm` crates talking directly to Linux KVM. The hard parts include implementing fast microVM initialization (<10ms), custom virtio-fs and networking devices, dirty-page tracking for live memory checkpointing/snapshots, and multi-tenant isolation guarantees. This necessitates low-level OS/virtualization engineers with extensive KVM and systems experience.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 154 launches clear the similarity bar, closest 8 shown.
Attention rank: #129 of 155 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 252 days after the earliest competitor.
- Superserve · hn · 2026-07-21 · 9 upvotes · similarity 0.55
- We built a <60ms, open-source alternative to E2B using RustVMM and KVM · hn · 2026-04-22 · 7 upvotes · similarity 0.52
- Sub-millisecond VM sandboxes using CoW memory forking · hn · 2026-03-17 · 311 upvotes · similarity 0.50
- jurniti · ph · 2026-09-15 · 70 upvotes · similarity 0.46
- BVisor · hn · 2026-02-23 · 24 upvotes · similarity 0.46
- Hyper · hn · 2026-07-09 · 5 upvotes · similarity 0.45
- Clawbernetes · hn · 2026-02-20 · 5 upvotes · similarity 0.43
- lingcage · github · 2026-09-12 · 11 upvotes · similarity 0.42
Other launches for this product
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.