Skip to main content
Run your first Fleet Prime Agent turn in under five minutes. This page uses the CLI. For the web UI or TUI, see Interfaces after you finish here.

Prerequisites

  • Node.js 22.8.0 or newer
  • npm 11.10 or newer
  • pnpm 11 or newer (only needed for the web app)
  • Python 3.10 or newer (for the IPython kernel used by every session)
  • An API key or OAuth account for at least one provider (see Providers and models)

1. Install

Clone the repo and install the agent workspace.
The .npmrc in the repo pins a 7-day min-release-age on dependencies. The first npm ci may take a minute longer than usual because of that. For the full install matrix — web app, kernel Python, IDE integration — see Install.

2. Sign in a provider

Start the agent CLI once and use the /login slash command to add credentials for a provider.
At the prompt:
Pick a provider from the list and paste an API key, or complete the OAuth flow if the provider supports it. Credentials are stored in ~/.prime/agent/auth.json with mode 0600. You can also pass a key inline for a single run without persisting it:
For the full flag list see the CLI reference.

3. Run your first turn

Ask the agent to do something that exercises the IPython kernel:
You will see:
  1. A thinking card while the model plans.
  2. An IPython tool card that lists directories and runs a Path glob to count files.
  3. A shell tool card if the model reaches for find instead.
  4. A final assistant message with the result.
Every card is a ChatStreamEvent — see Streaming protocol for the wire format.

4. Try a subagent

Inside an IPython cell the model can call rlm(...) to spawn a child agent. Ask:
The parent turn keeps streaming while the children run. Each subagent shows up as its own tool card with its own transcript. See Subagents (RLM) for how the runtime schedules them.

5. Save what worked with /refine

If the run went well, refine the agent’s supplemental state so it does better next time:
/refine reads the trajectory, extracts evidence, and updates supplemental harness state. It never rewrites the immutable base prompt, and it takes a snapshot so you can roll back. See Refinement.

Next steps

Learn the concepts

Architecture, sessions, subagents, streaming events, refinement.

Try more features

Guides for tool cards, providers, session branching, slash commands, MCP, OAuth.

Pick your interface

CLI, TUI, daemon, or the Qredence web app.

Configure and secure

Config paths, environment variables, security model.
Last modified on August 17, 2026