Wolfpack – Private control room for coding agents Wolfpack, a self-hosted browser terminal dashboard for AI coding agents including Claude Code, Codex, and Gemini, has been released. It runs on macOS/Linux machines and provides a PWA command center for persistent agent terminal sessions across a Tailscale tailnet, with sessions managed by a Rust PTY broker to survive server restarts. The tool is agent-agnostic, supports multi-machine views, and is available via a curl installer or package runners like bunx and npx. Wolfpack is a self-hosted browser terminal dashboard for AI coding agents: Claude Code, Codex, Gemini, shell commands, and custom agent wrappers. It runs on your own macOS/Linux machine — laptop, workstation, or cloud VM — and gives you a PWA command center for long-running agent terminal sessions across your Tailscale tailnet. Sessions live in a Rust PTY broker, not the web server, so server restarts and redeploys do not kill your agents. There is no Wolfpack-hosted relay or account; remote access is normally handled by Tailscale https://tailscale.com/ . Try the workflow: install Wolfpack on two machines, connect them to the same Tailscale tailnet, then open the phone QR from either host to control persistent agent sessions remotely. Start with the Quickstart quickstart and First five minutes first-five-minutes . curl -fsSL https://raw.githubusercontent.com/almogdepaz/wolfpack/main/install.sh | bash wolfpack The installer downloads the right pre-built binaries for your platform, runs setup, and can install Wolfpack as a login service. Wolfpack's phone and remote-control workflow uses Tailscale; setup can install it, waits for sign-in, then verifies its private HTTPS route before it prints a phone QR code. The bundled wolfpack-broker includes its Ghostty VT engine; release installs do not need Zig, Ghostty, or extra system libraries. Supported: macOS arm64/x64 and Linux x64/arm64. Want a package runner instead? Pin @latest so Bun/npm does not reuse an older cached release: bunx wolfpack-bridge@latest or npx --yes wolfpack-bridge@latest Both package-runner commands resolve the same matching prebuilt wolfpack and wolfpack-broker pair as the curl installer, then run the same setup wizard. Unlike curl, they do not add wolfpack to your shell PATH ; use curl when you want a persistent CLI installation. If setup gets weird, run: wolfpack doctor Uninstall is explicit: wolfpack uninstall --yes - Run the installer. - Choose your projects directory and port. On a fresh install, setup enables shell plus supported providers detected on PATH ; existing agent settings are never overwritten. - Sign in to Tailscale when setup opens it macOS or prompts for sudo tailscale up Linux . Setup keeps the same run open for retry. - Setup configures and verifies tailscale serve before it prints the private Tailnet HTTPS QR code. - Install the service when prompted if you want Wolfpack and its agents reachable after login/reboots. - Scan the QR code, open Wolfpack on your phone, then Add to Home Screen . - Create a session and pick an agent command. A local browser can still open Wolfpack on the host machine. It is not phone access: only a verified Tailnet HTTPS QR code opens Wolfpack from another device. Use Wolfpack when you want a self-hosted alternative to juggling tmux panes, SSH windows, and cloud workspaces for AI agent sessions. It is an AI agent terminal orchestrator for developers who need persistent browser/mobile access to coding agents running on machines they control. Phone-first agent control — respond to Claude/Codex/Gemini while away from your desk. Multi-machine view — manage sessions from every machine in your tailnet, including cloud VMs. Persistent PTYs — the Rust broker owns sessions, so server restarts do not kill agents. Session triage — cards show running/idle/needs-input state and live output previews. Desktop grid — view up to 6 terminals side by side. PWA UX — install on your home screen, reconnect on drops, receive notifications when sessions need attention. Agent-agnostic — use built-in commands or add your own shell command in Settings → Agents. Provider readiness — First-run setup enables detected supported CLIs; Settings → Agents shows path/version and login guidance and lets you add providers installed later. Pi integration — optionally install Pi packages for Wolfpack session control and durable subagent task delegation; see Pi integration and agent skills pi-integration-and-agent-skills . Wolfpack starts sessions by running a command in the selected project directory. Configure commands in Settings → Agents . | Agent | Command | |---|---| | Shell | shell | | Claude Code | claude | | Codex | codex | | Gemini | gemini | | Cursor | cursor | | Pi | pi | | Custom wrapper | any command on PATH , for example opencode or my-agent --flag | cmd validation intentionally rejects shell metacharacters for session commands. If you need complex setup, put it in a wrapper script on PATH and add that command. wolfpack Start the server runs setup on first launch wolfpack setup Re-run the setup wizard wolfpack list --json List active broker sessions wolfpack session create Create a top-level project session wolfpack agent spawn Spawn a same-harness child agent wolfpack session ... Status/read/send/wait/prompt helpers for agent automation wolfpack attach name Attach the local terminal to an existing session wolfpack kill