Docs

Run an agent on its own computer.

Start with the first guide: it takes you from one free click to a real task, terminal access, and billing only when you need it. The remaining guides explain individual capabilities. For connecting your own MCP client, see the MCP guide; for plans and credits, see pricing.

Quickstart — start here

Start free, give the agent a real first task, connect your terminal, and add credits only when you outgrow the trial.

plori CLI

Install the CLI, complete browser login, run an agent, use JSON output in scripts, and keep API-key auth for CI.

Disk and files

How a plori agent's persistent disk works: the account disk pool, the files panel, what persists, and buying more space.

Publish a site

Turn one directory of an agent's disk into a website at your-name.plori.site. Private by default, served while the agent sleeps, and how visibility works.

Agent memory

plori agents keep notes about you and your projects. How memory works, private vs account scope, and how to manage it.

Scheduled runs

Ask an agent to do something later. How schedule_run works from chat and MCP, and how the result comes back to you.

Background tasks

Long-running work keeps going after the reply. How plori backgrounds slow tool calls and posts the result back into the conversation.

Workflows

Standing automations your agent builds in chat: schedule, webhook, and manual triggers, safe test runs, credentials, per-run pricing, and plan limits.

Bring your own model key

Connect your own model provider key (OpenRouter one-click, or a pasted key) so model usage bills to your provider account instead of credits.

Every page here is also available as plain Markdown: request it with an Accept: text/markdown header. Agents can start from llms.txt.