up to $20

Docs

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 gives you an AI agent running in its own persistent environment. Each agent has a persistent disk, shell access, and network. Start one, give it a real task, connect from your terminal, and add credits only when the free allowance runs out.

1. Start free

Open plori.ai and choose Start free. One click creates a trial agent in its own environment and opens its chat. There is no signup, email, or card before the agent starts.

The plori trial includes $1 of credits, 128 MB of disk, and 1 agent kept for 7 days.

2. Give it a first task

Ask for a result that uses the environment and leaves something behind:

Research the latest releases of the project I name, compare the changes, and save a concise report to work/report.md.

The agent can use its shell and web tools, install what it needs, and save the report on its persistent disk. Open the Files panel to verify the file exists; ask a follow-up in the same chat to see that the work carries forward.

3. Keep it, then use your terminal

Sign in before the seven-day trial expires. The same agent, conversations, and files move into the registered account. Continue with Google in one round trip, or use a six-digit email code. Neither sign-in path asks for a password or card. When signup rewards are available, eligible new Google signups can receive up to $20 in welcome usage right away. Email signups start with the $1 trial.

Install the CLI and sign in through that same browser flow:

curl -fsSL https://plori.ai/install.sh | sh
plori login
plori create mate
plori run mate "Create a short project brief and save it to work/brief.md"

plori login opens the email-code page and returns to the terminal when complete. The installer needs no sudo and no Node; npm i -g @plori/cli installs the same binary if you prefer npm. It installs to ~/.local/bin and does not touch your shell config, so if that directory is not on your PATH yet, add it first with the line the installer prints.

For a back-and-forth session instead of one-shot commands, attach to the agent:

plori attach mate

That is the same conversation the web app shows, with history, streaming output, and approvals in the terminal. Ctrl-D detaches and leaves the run going. The CLI guide has the full command list, token location, CI authentication, and JSON output.

To connect from Claude Code, paste this into your conversation:

Set up https://plori.ai/SKILL.md

If Claude asks, type /reload-plugins to load the MCP server, then continue in the same conversation. Follow the sign-in and approval steps; no plugin installation is required.

4. Pay only when you outgrow the free allowance

A registered Free account includes $5 of usage per month and 1 GB of account disk. Accounts that sign in with Google also include 2,000 minutes of run time a month. An account created with an email code only pays for run time from the first minute, the same as the anonymous trial. Eligible signup paths may also include a one-time welcome top-up of up to $20, as described above. The Plori Router picks one model per request from a pool shared by every plan. The pool changes as models are released and repriced, and each run's usage shows which model served it.

plori warns you before the credit balance reaches zero and links to billing. Stay on Free while it fits. When it does not, compare plans: paid plans add more agents, concurrent runs, and larger disks. To use a specific model, including frontier models such as Claude Opus 4.8 and GPT-5.6 Sol, bring your own key. For a temporary spike, add one-time credits without changing plans.

Idle agents sleep and stop billing for compute. Their disk, files, and memory remain, so the next task starts from the state the previous one left behind.

Composer shortcuts

The message box in the web terminal reads three prefixes while you type. Each one opens a menu that you move through with the arrow keys and accept with Tab or Enter.

  • / lists the commands this agent accepts.
  • @ lists your other agents and inserts the name you pick.
  • $ lists the skills on this agent's disk.

A skill is a written procedure the agent reads before it starts work. plori supplies skills for common jobs, such as publishing a site, and the agent writes more as it learns your tasks.

To use a skill:

  1. Type $ in the message box.
  2. Type part of the skill name or description. The menu shows fewer items.
  3. Press Tab. The composer writes $name into your message.
  4. Write the rest of your message and send it.

The agent loads that skill for the turn, so you do not describe the procedure again. To close the menu without picking anything, press Escape.

The menu stays closed for a $ inside a word, for a price such as $20, and for a shell variable such as $PATH. The agent receives these as you wrote them. An agent that has not run yet has no skills, so the menu is empty until after its first task.

Next