wavyrai/tmux-ide

The open-source tmux for your coding agents

What it solves

It provides a centralized workspace for managing and coordinating multiple coding agents (like Claude Code and Codex) running in tmux sessions. It solves the problem of tracking the status of various agents across local and remote machines, allowing users to quickly identify which agent needs attention or is currently working.

How it works

The project builds on top of existing tmux sessions rather than replacing them. It uses a daemon to handle discovery, agent state, and pane streams, while a dedicated app provides a user interface for the Home screen, terminal mirroring, and input controls. Because it relies on tmux for process and session persistence, agents continue to run even if the tmux-ide app is closed.

Who it’s for

Developers who use terminal-based coding agents and tmux to manage their development environment, especially those who coordinate teams of agents across local and remote SSH machines.

Highlights

  • Agent Status Tracking: Monitors whether agents are working, blocked, done, or idle via hooks or screen reading.
  • Multi-Agent Coordination: Supports grouping agents into teams and coordinating them via CLI commands like send and wait.
  • Remote Access: Manages sessions across local and remote machines over SSH side-by-side.
  • Session Persistence: Allows restoring conversations and sessions after crashes or reboots.
  • tmux chrome: Adds a status bar, sidebar, and keys to standard tmux clients.
  • Scripting SDK: Provides an SDK and MCP support for scoped pane reads and sends.

Related

  • Project
    safedep/pmg

    Package Manager Guard (PMG) is a security tool that intercepts package manager commands to block malicious dependencies and restrict installation scripts using sandboxing and threat intelligence.

  • Project
    llmmanorg/llmman

    llmman is a CLI/daemon that runs any LLM‑style agent (Claude Code, Codex, Copilot, etc.) on any model—local or hosted—by treating models as OCI container images. It supports multiple back‑ends (llama.cpp, vLLM, sglang, mlx‑lm), provides a unified Ollama/OpenAI/Anthropic API, enables registry‑to‑registry model transfer, signing with cosign, and aggregation of several machines into one endpoint.

  • Project
    giovtorres/slurm-docker-cluster

    A multi-container Slurm cluster deployed via Docker Compose for rapid development, testing, and lightweight HPC job scheduling.

  • Project
    hyperactive-project/Hyperactive

    A unified Python interface for hyperparameter tuning and black-box optimization that separates optimization problems from algorithms across multiple backends.