Tarit – Self-host sandbox cloud and hypervisor for AI agents
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…
What it does
In the maker’s words, at launch
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...
Does the same job
all alternatives →
npm i -g hotcellAug 2026 · github.com · ▲97Local sandboxes for AI agents on your Mac, Linux, bare metal
- WBWe built a <60ms, open-source alternative to E2B using RustVMM and KVMApr 2026 · github.com · ▲7
Over the past few months, as we scaled our internal AI Agents, we hit a dead end: Running LLM-generated arbitrary code in Docker is basically running naked on security due to container escape risks. But using full traditional VMs takes minutes to boot and eats too much memory to support high-density concurrency. We loved the developer experience of SaaS sandboxes on the market, but they are closed-source, expensive, and have too high a barrier to entry for self-hosting. So, our team decided to build our own. After months of grinding, using RustVMM and KVM, we built a blazing-fast,…
- SFSuperserve – Firecracker microVM sandboxes for long-running AI agentsJul 2026 · superserve.ai · ▲9
Hey HN, I built Superserve, a compute layer that lets AI agents live inside isolated Firecracker microVMs with no session time limits. The problem I kept running into: most sandbox providers kill your agent after 24 hours. If you're running something autonomous that needs to work for days — refactoring a codebase, running tests in a loop — you're constantly fighting timeouts and rebuilding state. Superserve lets you snapshot a running VM at any point, fork it into parallel branches, and resume exactly where you left off. Each agent gets its own VM, no shared kernels. There's also a…
- LVLaunch VM workloads securely and instantaneously, without VMs2021 · ▲12
Hello HN! We've been working on a new hypervisor https://kwarantine.xyz that can run strongly isolated containers. This is still a WIP, but we wanted to give the community an idea about our approach, its benefits, and various use cases it unlocks. Today, VMs are used to host containers, and make up for the lack of strong security as well as kernel isolation in containers. This work adds this missing security piece in containers. We plan on launching a free private beta soon. Meanwhile, we'd deeply appreciate any feedback, and happy to answer any questions here or on our slack…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
