> ## Documentation Index > Fetch the complete documentation index at: https://docs.prbe.ai/llms.txt > Use this file to discover all available pages before exploring further. # Install Probe > The guided install, screen by screen: pick your agents, review what gets set up, install, import. ```bash theme={null} npx probe-research install ``` Four numbered screens. The first is skipped on a machine with only one coding agent, and the numbering adjusts so you are never told you are on step 2 of 4 when there are three. Between the last two, the wizard asks one question when your team has more than one workspace: where this computer's work should go. **1. Sign in** Before any screen, the wizard authorizes this device. It opens your browser; you approve there. Nothing is pasted. If you were given a ten-character code on the website, pass it as an argument and the wizard uses it instead: ```bash theme={null} npx probe-research install ABCD123456 ``` On a device that already holds a credential, the wizard asks whether to keep the current account or continue with the website code — that is how a wrong-account install gets corrected. **2. Coding agents** Which agents to set up: **Claude Code**, **Codex**, **pi**, **Kimi Code**, **Capy**, or several. Detected agents are pre-ticked; `Space` toggles, `Enter` continues. Capy is listed when its app is on this computer; see [Capy](/agents/capy.md). This screen does not appear when the machine offers no choice. > [!NOTE] > > Each agent gets its own capture credential and its own plugin directory. They are configured independently and can fail independently — which is why the summary line shows MCP and capture per agent, not once for the device. **3. Review and install** Everything that is about to be set up, in plain terms. There is no capability picker here on purpose: the install is complete by design, and this screen is what carries the disclosure. > **CLI + MCP** > > Skills for tracking runs, and read-only search over your lab's history. > **Session capture** > > Streams your Claude Code, Codex, pi or Kimi Code sessions to your team's knowledgebase. Sends **your prompts, the assistant's replies, and the shell commands you run**, not file contents and not tool output. > > For **Capy**, it copies the threads you start, in the Capy projects you choose, every 10 minutes through Capy's API: the installer asks for your Capy API key after this screen, and leaving it empty skips Capy capture. See [Capy](/agents/capy.md). > > Credential-shaped values are replaced before upload, but that is a filter and not a guarantee, so keep live credentials out of your prompts. Captured sessions are visible to your whole team. > > It is per-device, disclosed here and again at the browser approval, and `probe wizard --no-capture --yes` turns it off at any time. See [Session capture](/agents/capture.md#turning-it-off). > **Automatic updates** > > Keeps the CLI and plugins current in the background at session start. > **Rules in your global instructions** > > A managed Probe block in each selected agent's global instruction file, prompting it to search Probe and track research there. The block is managed — `probe agent-rules refresh` rewrites it when it falls behind the CLI — and everything around it is left alone. `Enter` installs. `Esc` goes back. **4. Installing** The marketplace is added, both plugins are installed for each selected agent, the capture credential is paired, and the managed rules block is written. Progress is per-stage, not a single indeterminate bar. Nothing here needs input. If an agent fails, the others still complete and the failure is named rather than rolled into a generic error. **5. Where should this computer's work go?** Every new project made on this computer, by your agent, the Probe daemon or an SDK run, is filed in one workspace. The wizard lists your team's workspaces, starting on the one this computer already uses, and offers **Create a new workspace**. Your pick is saved for this computer, the same setting `probe workspace use` writes. A team with one workspace is not asked. An unattended install (`--yes`, or no terminal) never guesses between several: it keeps this computer's workspace, else your saved one, else leaves it unset and says how to pick. This step never blocks a finished install. **6. Import existing work** The install is done; this screen offers to bring your history in. * **Import past coding sessions** — reads the selected agents' saved transcripts; asks before anything uploads. * **Import a folder of project work** — an agent reads the folder, uploads what it finds and describes it. Neither is ticked for you. Continuing with nothing selected is a real answer, not a failure state — you can come back to this from the main menu at any time. See [Import research work](/wizard/import.md) for what each one does. ## After the install The final page shows compact live progress for both kinds of import, sessions first. You can exit while they run. To confirm the install independently: ```bash theme={null} probe doctor ``` In Claude Code, the install also added a status indicator under the input box. It renders `● tracking → folding`, `● tracking → folding · running` or `● read-only`, and keeps whatever status line you already had; Uninstall removes it and restores that. See [Status line](/agents/statusline.md). Your agent records its own work, unless the other coding agents on this computer already record through [the Probe daemon](/agents/daemon.md): a newly set-up agent joins them. To switch, use **Who records** on the wizard's main menu. ## Doing it without the wizard ```bash theme={null} probe wizard --action manual ``` Prints every command the wizard would run, for the agents you name. It is generated from the same constants the wizard uses, so it cannot drift from what the wizard actually does. This is the path for air-gapped machines and for anyone who wants to see the commands before running them. See [Installation](/installation.md) for the commands themselves. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.