DigestAI news desk

Cut through the AI noise.

Agents & Tools3 min read

gPTY: Godot‑Rust Terminal Multiplexer Enables AI‑Driven Workspace Control

gPTY is a new terminal multiplexer built on Godot and Rust that offers a tiling grid for terminals, code editors, file trees, and more. It exposes a JSON‑RPC/MCP control surface, allowing AI agents and automation tools to spawn panes, inject text, and observe terminal output without scraping a text‑user interface.

1 source primary source HN 41

Key points

  • gPTY is a Godot‑Rust terminal multiplexer that exposes JSON‑RPC/MCP for AI agent control
  • It captures PTY output via regex triggers and routes it to adjacent panes without injecting input
  • Standalone binaries for Linux, macOS, and Windows are available, with full persistence and observability features

The core of gPTY is a PTY foundation that manages independent shell sessions in a resizable grid, complete with full‑color support, regex‑based scrollback search, and wrapped text selection. A concept capture engine watches PTY output for regex triggers and routes responses to adjacent panes, while an observability pane logs agent lifecycle events. All state—scrollback, settings, workspaces, and profiles—is persisted to SQLite/JSON and restored on restart.

The project is distributed as standalone binaries for Linux, macOS, and Windows, and its CLI and MCP server enable AI agents to control the workspace programmatically. The codebase was largely generated by large language models, and the project is released under the GPL‑3 license with permissive exceptions for extensions.

Full story from github.com · via Hacker News primary sourceOpen source ↗

Godot and Rust based multiplexer (terminal panes and more)

github.com · 11 September 2026

Loading the full article…

This text was published by github.com. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

1source
Topics · follow one to build your own front page
Neil Pathare

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Agents & Tools

All →

Related stories