tmux

lazy-tmux is a CLI tool that snapshots tmux sessions with running processes and scrollback, and restores them lazily when selected from a TUI picker.

A developer describes a multi-agent hive using tmux that allows agents to downshift their own model (e.g., from Fable to Sonnet) automatically, and upshift with permission via Telegram.

A developer details Observation-Oriented Programming (OOP), a paradigm for organizing a swarm of terminal AI agents around watching observability data rather than task execution. The system uses tmux, cron, bash, and an append-only log file, with agents acting as observers that correlate signals and materialize actions only after interpretation.

This thread describes a secure and reliable development setup for agentic AI using a dedicated server accessed via SSH with tmux for session persistence, a terminal emulator with native tmux integration, and a VPN for secure access. The author advocates for this over local agent execution due to security and reliability concerns.

A developer criticizes Kubernetes' deployment method as too complex, advocating for using tmux sessions and while true loops to simply manage service processes, believing this approach has sufficient performance and is easy to maintain.

Introducing rmux, a modern terminal multiplexer written in Rust, designed for AI Agent and automation scenarios. It coordinates multiple Agents running simultaneously, is compatible with over 90 tmux commands, and offers a Python SDK and browser-based session sharing.

Former Meta/Microsoft/Atlassian staff engineer Kun shares his agentic engineering workflow: centered on terminal, tmux, and Neovim, using global/project-level memory files and skills to train AI teammates, delivering 40-50 tested production PRs daily, boosted by voice input, AXI standard, Lavish interactive planning, and more.

Recommends a comprehensive introduction to 'Agentic Engineering Workflow', covering tmux, agent memory, skills, voice input, long task execution, parallel worktree management, multi-agent scheduling, along with the visual HTML editor Lavish and a code change validation pipeline: no-mistakes.

A tmux plugin that lets you run multiple Claude Code sessions in separate tmux windows, with a central fzf picker showing live status and previews, and the ability to jump between sessions.

tmux-underkeys is a Tmux plugin that assigns mnemonic shortcut keys to session names by underlining a unique character in each session name, allowing instant keyboard-driven session switching via a configurable trigger key.

Tmux allows AI agents to persist after closing the terminal, enabling detachment and later reattachment.

Axel is a macOS app with a Rust CLI that orchestrates AI agents in isolated git worktrees and tmux panes, providing a task management interface for multi-agent workflows.

Pieter Levels shares his server workflow using Termius profiles and a custom tmux function that auto-attaches to per-site sessions, enabling seamless switching between devices and consistent work sessions.

Tips for using Grok Build to manage multiple machines via SSH and tmux sessions, as shared by Yun-Ta Tsai.

A Twitter thread outlines five foundational tools for building agentic systems: Tailscale for mesh networking, Termius for SSH access, tmux for persistent sessions, a private git repo for memory, and scripting everything from day one. The post emphasizes that these basics matter more than any specific model or framework.

Introduces a method to remotely connect to a home Mac Mini via Tailscale and Screen Sharing for a development environment, using tmux to maintain sessions and a consistent setup.

Shannon is a CLI and SDK wrapper that runs an interactive Claude Code session inside tmux, allowing programmatic querying and streaming JSON output by tailing the on-disk transcript.

Tmux-Orchestrator is an open-source tool that enables autonomous 24/7 operation of Claude AI agents using a multi-agent hierarchy within tmux sessions for parallel project management and coding.