yiwenlu66/PiloTY

PiloTY (PTY for your AI Copilot) is an MCP server that gives an agent a persistent, interactive terminal.
If you have used Claude Code / Codex to run shell commands, you have probably hit the same wall: tool calls tend to be stateless. Each call starts "fresh", so environment variables disappear, interactive programs cannot be driven reliably, and long-running processes get cut off or orphaned while the agent is thinking.
PiloTY exists to make the agent's terminal behave more like a human's: start something in a real terminal, come back later, and keep going.
Warning: PiloTY exposes unrestricted terminal access. Treat it like giving the agent your keyboard.
What it enables
- Long-running commands: builds, installs, migrations, test suites. Start once, check output later.
- Log monitoring: tail -f, journalctl -f, kubectl logs -f, CI logs, service restarts.
- "Vibe debugging": keep a REPL/debugger open while the agent reads code and tries ideas (python, ipython, pdb).
- Privileged operations: handle interactive password prompts (sudo, SSH passwords, key passphrases).
- SSH-based devops: keep a remote login session alive across tool calls; run remote commands in the same shell.
- Terminal UIs: less, man, top, vim can work, but cursor-heavy programs often require screen snapshots instead of plain text output.
Quickstart
PiloTY is meant to be launched by an MCP client over stdio.
Add it to Codex CLI as an MCP server:
If you prefer SSH-based Git fetch:
If you already have a local clone:
Run the server command directly (without adding it to an MCP client):
Mental model
One session is one real interactive terminal that stays alive across tool calls.
- State persists: cwd, environment variables, foreground process, remote SSH connection, REPL/debugger state.
- PiloTY tracks both the raw output stream and a rendered screen/scrollback view.
PiloTY keeps two representations:
- output: incremental text stream (optionally ANSI-stripped)
- Rendered screen/scrollback: what a human would see in a terminal
Public MCP results separate call outcome from terminal interpretation:
- outcome: success, deadline_exceeded, eof, error, invalid_session, or terminated
- terminal_state: best-effort rendered-state classification after the call (running, ready, password, confirm, repl, editor, pager, unknown)
Sessions are addressed by a session_id string. Reusing the same id is what keeps state.
Integration notes (for MCP integrators)
MCP does not expose a standard "client cwd" field, so the first step is always to create a session with an explicit working directory, then reuse the same session_id for subsequent calls.
Typical agent workflow:
- Create a session (explicit cwd) and reuse the same session_id.
- Use send_line to submit a newline-terminated command, send_text for raw bytes, and send_control / send_signal for interrupts.
- Use wait_for_output for temporal PTY output waiting, wait_for_regex for content-based waits, and wait_for_shell_prompt after ssh or similar login flows.
- Use snapshot_screen / snapshot_scrollback when layout matters. Snapshot tools are passive and do not ingest fresh PTY bytes.