> ## Documentation Index > Fetch the complete documentation index at: https://docs.byterover.dev/llms.txt > Use this file to discover all available pages before exploring further. # Quickstart > Get productive with ByteRover CLI in under 2 minutes ## Prerequisites * ByteRover account ([sign up](https://app.byterover.dev)) * An active team and space in [ByteRover's web app](https://app.byterover.dev) * [Node.js 20+](https://nodejs.org/en/download/) * Your coding agent IDE (Cursor, Claude Code, Windsurf, etc.) with a project opened and a terminal created to run `brv` commands Our CLI uses `libsecret` for secure credential storage. Install it for your distribution: * **Debian/Ubuntu:** `sudo apt-get install libsecret-1-dev` * **Red Hat-based:** `sudo yum install libsecret-devel` * **Arch Linux:** `sudo pacman -S libsecret` ByteRover CLI runs in WSL but requires your development environment to be fully within WSL: * **Environment Separation** * Windows and WSL are separate environments with their own file systems and installed programs * If you install ByteRover CLI in WSL, your coding agents must also be able to access the WSL environment. * Example: If using Claude Code, install it with `npm install -g @anthropic-ai/claude-code` from a WSL terminal * **Why this matters** * A coding agent running on Windows cannot access the CLI installed in WSL (and vice versa) * Project files should be in the WSL file system (`~/projects`) for best performance, not `/mnt/c/...` * **Known Limitations** * WSL may experience occasional performance slowdowns or stability issues compared to native Linux or macOS * File operations across the Windows/WSL boundary (`/mnt/c/`) are significantly slower * We recommend using WSL 2 for better compatibility * **Credential Storage** * ByteRover CLI automatically uses secure file-based storage in WSL (system keychain is not accessible) * Credentials are encrypted with AES-256-GCM and stored in `~/.local/share/brv/` ByteRover CLI is designed as an interactive terminal application and **does not support headless server environments**: * **Interactive Terminal Required** * The REPL requires a TTY-enabled terminal * Won't work in CI/CD pipelines, cron jobs, or backgrounded processes * **Browser Authentication Required** * OAuth login launches your system's default browser * Headless servers cannot complete the authentication flow * **Desktop Credential Manager Required (Linux)** * Uses `libsecret` which requires dbus and a desktop environment * Server Linux distributions lack these components * **Unsupported Environments** * Headless Linux servers (Ubuntu Server, CentOS, etc.) * Docker containers without TTY (`-it` flags) * CI/CD pipelines (GitHub Actions, Jenkins, etc.) * SSH sessions without pseudo-terminal allocation ## Step 1: Install ```bash theme={null} npm install -g byterover-cli ``` Verify the installation: ```bash theme={null} brv --version ``` ## Step 2: Authenticate Navigate to your project directory and start the ByteRover REPL: ```bash theme={null} cd path/to/your/project brv ``` For the firs time, Byterover prompt you to complete authentication on the browser: Follow the browser prompt to complete authentication. Later, if you want **re-authenticate**, type this: ```bash theme={null} /login ``` ## Step 3: Initialize your project After authentication, you'll see this wecome message: Hit `Enter` and you'll complete a quick setup: After completing the setup, ByteRover will sync your remote context and based on your chosen coding agent, a **default connector** is selected. You can also **re-initialize** your project by using this slash command: ```bash theme={null} /init ``` To view or change your connectors, use the `/connectors` command: ```bash theme={null} /connectors ``` For more details on connector types and supported agents, see [Coding Agent Connectors](/connectors/overview). ## Step 4: Add your first context ### Via your coding agent Prompt your coding agent (Cursor, Claude Code, Windsurf, etc.): ``` > Use brv curate command to curate essential contexts of this project's unit testing strategy. Make sure that unit tests run fast and run completely in memory. ``` Your coding agent will analyze the codebase and use `brv curate` to add context automatically. You can view the operation in progress in Byterover's TUI. For full detail, use `Ctrl + o` to view the full response: ### Manual Use the `/curate` command for more intentional curation: ```bash theme={null} /curate make sure that unit tests run fast and run completely in memory ``` ### Context Tree In this example, ByteRover organizes it into `testing`, one of the structured domains (`structure`, `database`, and `backend`, etc.) in the context tree (located at `.brv/context-tree`). To learn more about the context tree structure, see [Local Context Tree Structure](context-tree/local-space-structure.mdx). ## Step 5: Verify it worked Check your context tree with: ```bash theme={null} /status ``` You'll see your newly curated context added to the local context tree, ready to be synced to your remote space. ## Step 6: Query context ### Via your coding agent Prompt your coding agent to retrieve context before implementing: ``` > Use brv query command to check what unit testing strategies are in this project ``` Your coding agent will run `brv query`, asking what it needs for its task, and get the precise context. ByteRover will retrieve the exact context curated earlier—unit testing strategies for the coding agent. ### Manual In the TUI, use the `/query` command: ```bash theme={null} /query "What are unit testing strategies in this project?" ``` To view the operation in progress, use `Ctrl + o` for full response mode: **Codex users: Network access required** Codex runs in a sandboxed mode without internet access by default. To use ByteRover CLI commands: 1. Switch to **Agent (full access) mode**, OR 2. Add to your prompt: *"You can ask me about network access and I will allow it"* 3. Approve network access when prompted *** **You're all set!** You now know the core ByteRover commands. Continue learning how to collaborate with your team and integrate ByteRover into your complete workflow. ## Next steps Sync context with your team and see the complete workflow cycle Learn best practices for adding context effectively Master context retrieval techniques Quick patterns for onboarding new projects