Alternatives
Products that do what I'm running parallel Pi agents on a local sandbox does
I've been running Pi using SmolVM to build SmolVM! SmolVM provides an abstraction over microVMs to easily create sandboxes for coding agents, OpenClaw, or just to build a custom harness. To use it, install using: curl -sSL https://celesto.ai/install.sh | bash and then run: smolvm pi start
- 1SO
SmolVM is an open-source local sandbox for AI agents on macOS and Linux. I started building it because agent workflows need more than isolated code execution. They need a reusable environment: write files in one step, come back later, snapshot state, pause/resume, and increasingly interact with browsers or full desktop environments. Right now SmolVM is a Python SDK and CLI focused on local developer experience. Current features include: - local sandbox environments - macOS and Linux support - snapshotting - pause/resume - persistent environments across turns Install: ``` curl -sSL…
Apr 2026 · github.com
- 2SM
I wanted to see how fast an isolated code sandbox could start if I never had to boot a fresh VM. So instead of launching a new microVM per execution, I boot Firecracker once with Python and numpy already loaded, then snapshot the full VM state. Every execution after that creates a new KVM VM backed by a `MAP_PRIVATE` mapping of the snapshot memory, so Linux gives me copy-on-write pages automatically. That means each sandbox starts from an already-running Python process inside a real VM, runs the code, and exits. These are real KVM VMs, not containers: separate guest kernel, separate guest…
Mar 2026 · github.com
- 3
- 4
- 5RC
Hi HN, we built SuperHQ, an open source app that runs AI coding agents in isolated microVM sandboxes instead of directly on your machine. Each agent gets its own VM with a full Debian environment. You mount your projects in, writes go to a tmpfs overlay so your host is never touched, and you get a diff view to accept or discard changes. API keys never enter the sandbox. We also just launched remote.superhq.ai which acts as a remote control for SuperHQ, allowing you to access your workspaces and agents from anywhere.
Apr 2026 · github.com
- 6IV
2013 · jondot.github.io
- 7
- 8
Local sandboxes for AI agents on your Mac, Linux, bare metal
Aug 2026 · github.com
- 9
- 10
- 11RA
Hey HN, I built SuperHQ, an app that lets you run coding agents in local sandboxes (powered by Shuru). No custom UI wrapping the agents, they run as CLI/TUI like they were designed to. It just provides you the tools most of us (okay, maybe just me?) needed for running multiple coding agents in parallel without worrying about breaking your system or work environment. Each agent runs in its own microVM. You mount your projects in, writes go to a tmpfs overlay so your host is never touched, and you get a unified diff view to accept or discard changes. API keys never enter the sandbox, they…
Apr 2026 · superhq.ai
- 12CA
2018 · cattlepi.com
- 13WB
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,…
Apr 2026 · github.com
- 14PH
I built that initially for an AI chat bot that allows teams to perform DevOps tasks straight out of Slack/Teams (with proper permission control, obviously). Useful to let developers perform mundane tasks, or help coordinate incident response. I ended up using it myself on my own machine to manage Hetzner and AWS boxes. I thought that may be useful to others. The default policy should be good enough, but if you don't like living dangerously, you can set it to `paranoid`. Install: `pi install npm:pi-hosts` GitHub: https://github.com/hunvreus/pi-hosts
Apr 2026 · github.com
- 15LR
I built localLLLM: a small community project for running local models. Live: https://locallllm.fly.dev The goal is simple: if someone has model + OS + GPU + RAM, they should get steps that actually work (ideally one liner) I need help populating and validating guides. If you run local models, please submit one working recipe (or report what failed). Would love to hear general feedback as well!
Apr 2026 · locallllm.fly.dev
- 16IB
Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
Jan 2026 · github.com
- 17RA
Hi HN folks, I have been building AI agents for quite some time now. The shift has gone from LLM + Tools → LLM Workflows → Agent + Tools + Memory, and now we are finally seeing true agency emerge: agents as systems composed of tools, command-line access, fine-grained system capabilities, and memory. This way of building agents is powerful, and I believe it is here to stay. But the real question is: are the systems powering these agents ready for that future? I do not think so. Using Docker for a single agent is not going to scale well, because agents need to be lightweight and fast. LLMs…
Mar 2026 · github.com
- 18
- 19SF
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…
Jul 2026 · superserve.ai
- 20MR
Microterm is a fully compliant Linux virtual machine that runs in any browser tab. It is designed for real development and operations workflows, not demo-only terminal output. You can use it on desktop, tablets, and phones, including iOS home-screen PWA installs. Under the hood, Microterm combines Restty (libghostty + WebGPU) web terminal rendering and a TinyEMU-backed Alpine Linux guest on RISC-V64. The VM image is chunk-loaded in the browser and booted locally. I successfully used it to run Codex directly without leaving an in-app preview inside X app or Telegram :) Can be used to SSH to…
Feb 2026 · microterm.dev
- 21SA
Hey HN! We’re building the StoffelVM, a virtual machine designed to make secure multi-party computation accessible to regular developers. Right now it’s early-stage: - We’ve built the VM core - But MPC isn’t wired up yet We are looking for feedback on the general approach. If you are interested in building something that would be a good fit, feel free to reach out! Details are in my bio.
2025 · github.com
- 22RS
Hi HN! I've been hacking on this side project for the last month or two with the goal of making it dead simple to use cloud GPUs. I ran into this problem personally during the phd, and built my own tooling around it. I always thought it'd be fun to try to turn that tooling into a more general product... and bitbop.io is the result! All you have to do is run `ssh bitbop.io`, and you get your own personal dev GPU workstation in the cloud. Looking forward to hearing your thoughts!
2024 · twitter.com
- 23
- 24MO
Hi HN, I'm Jonathan. My co-founder, Thomas, and I started building Mistle in Feb. We saw larger tech companies like Ramp (Inspect) and Stripe (Minions) build this internally and thought an open source version should exist. We made a few very intentional decisions when working on this: 1. Credentials are kept out of the sandbox. Authorized access goes through a proxy, so agents do not directly receive credentials. 2. The harness is not our problem. We're not going to tackle things like memory, self-learning. 3. No magic. Configurations are explicit. You can bring your own keys for models,…
May 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →