Prerequisites
- macOS or Linux on arm64 or x64 (Windows is not supported)
- Node.js 22.12.0 or later
- Python 3.10 or later for the managed IPython kernel
1. Install
Install the published package globally from npm. It includes the production web workspace and links thefleet-agent command. On first launch, Fleet downloads and verifies the pinned Prime Agent runtime.
2. Start your workspace
Run Fleet Prime Agent from the project directory you want the agent to work in:127.0.0.1 and rejects non-loopback requests.
3. Add a provider and pick a model
On first use, add a model provider in Settings → Providers, or type/login in the composer. Then choose a model in the composer’s model picker. Credentials are stored by the engine under ~/.prime/agent/ and are shared with any existing prime-agent install.
See Providers and models for OAuth providers and OpenAI-compatible endpoints.
4. Run a turn
Type a request in the composer. The agent streams its work as cards: IPython cells, shell commands, file edits, plans, and subagents. Your session persists after you close the browser; reopen the workspace and resume it from the session list.Prefer a terminal?
The pinned engine’s TUI is available asprime-agent, and fleet-agent agent <args> runs the pinned engine CLI directly. See Terminal interface.
Next steps
Web workspace
Projects, tool cards, slash commands, attachments, and settings.
Sessions and projects
How sessions persist, resume, and map to projects.