The agent's own environment
Persistent cloud environments for AI agents.
A persistent cloud environment is a place in the cloud that belongs to one agent: a durable disk, a real shell with tools, and memory that stays with it. Some directories list it as a cloud computer for AI agents. plori gives you the agent and the environment together. Close the chat and the environment stays.
Opens your agent straight away, no signup needed.
What is in the environment?
§01A persistent disk
Real files the agent keeps, browsable and editable from the files panel. Repos, reports, datasets: they stay with the agent.
A real shell and tools
Git, code and research CLIs on PATH, and web search and fetch. The agent installs whatever else the job needs, and the installs persist.
Memory
Short notes the agent keeps about you and your projects, read at the start of every turn.
Isolation
One dedicated machine per agent. Nothing shared between accounts; your own agents keep separate private directories on the account disk.
Sleeps when idle
The environment's state is kept, compute stops billing, and disk within your plan is free.
Any driver
Use it from the web chat, or drive it from your own tools over MCP.
Why does persistence matter?
§02Most execution environments for agents are ephemeral sandboxes: useful for running a snippet, gone when the session ends. That shape forces every task to start from zero and makes "pick this up tomorrow" impossible without you building storage around it.
A durable environment changes what you can delegate. Hand an agent a codebase and let it keep working copies. Leave a half-finished job overnight and resume it by saying so, or schedule work for later and trust that the environment that wakes up is the one that remembers the context. A colleague with a desk, not a calculator with a chat window.
Questions, answered.
§03What is a persistent cloud environment for an AI agent?
It is a persistent, isolated environment in the cloud that belongs to one agent: its own directory on the account disk, its own shell and tools, its own memory. The agent works there the way you work on your laptop, and the environment outlives any single conversation. On plori every agent gets one automatically.
Is this the same as a 'cloud computer for AI agents'?
Yes. Directories and older writeups use that phrase for the same thing. We say persistent environment because it is bounded and headless: a real shell, a durable disk, and network access, but no screen or graphical desktop, so it is not a general-purpose computer.
How is this different from a code sandbox?
Sandboxes built for code execution are typically ephemeral: the filesystem is gone when the session ends, and persistence means wiring up snapshots yourself. A plori agent's environment is durable by default. Files written today are there next month, and the agent sleeps in place at zero compute cost instead of being torn down.
What software does the agent's environment have?
A real shell, git, Python, Node, and a baseline of code and research tools on PATH, plus web search and page fetch. Beyond that, the agent installs what a task needs, from language toolchains to CLIs, and those installs persist on its disk.
What does the environment cost when the agent is not working?
Nothing, within your plan. An idle agent scales to zero, so compute stops entirely, and the disk included in your plan is free. You only pay while it works, from one pool of credits.
Can I see what is on my agent's disk?
Yes. Each agent's dashboard page has a files panel where you browse its directories, open and edit text files in a code editor, upload files for it to work on, and download anything it made.
How big is the disk?
Your account has one disk that all your agents draw from: 1 GB on Free, 20 GB on Pro, 50 GB on Power, and you can buy more at 10 credits per GB per month on any plan.