celesto

how is it different from celesto? https://github.com/CelestoAI/celesto

that's why you need to use a sandbox. SmolVM can easily run Pi, codex and claude https://github.com/CelestoAI/smolVM

The majority of legacy systems run on the Windows operating system. It is hard to automate with computer-use agents because of weird pop-ups, lack of a DOM like browsers, random clicks, and cost at scale. We built an agent harness and sandbox to automate any legacy software. Our Windows Sandbox (SmolVM) is open-source and can be used with a Python SDK or CLI - https://github.com/CelestoAI/SmolVM We will also publish our agent harness benchmark report soon.

This is something solved by a bunch of new sandboxes including ours - SmolVM https://github.com/CelestoAI/smolVM

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

Launching SmolVM -- run claude and codex in sandboxed environment with full permissions worry free. It sucks to “press enter and accept changes” every few seconds while using coding agents. We made it easy to isolate the agent coding environment from the host (laptops). With a single command you get a claude/codex pre-installed sandbox ready with git credential to make you build a billion dollar business without making any mistake ;) To give it a try, head to the open-source repo and install SmolVM then run: "smolvm codex start" or "smolvm claude start --mount ./my-project" for a quick experiment.

Is there a relation to the similarly-purposed and similarly-named https://github.com/CelestoAI/SmolVM

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 https://celesto.ai/install.sh | bash smolvm ``` I’d love feedback from people building coding agents or computer-use agents. Interested in what feels missing, what feels clunky, and what you’d expect from a sandbox like this.

Also, I've been running OpenClaw using SmolVM on my macOS. It adds a hardware level isolation (using KVM). https://github.com/CelestoAI/SmolVM/blob/main/examples/openc...