#117117th of 143 in Coding agents and AI editors

tmuxai

Terminal assistant that reads your tmux panes and runs commands in an exec pane

Stars
2k
License
Apache-2.0
Last commit
Sep 2026
Last release
Sep 2026
Language
Go
Stars, last 29 weeks+292
31 Mar 2026: 1,672 stars7 Apr 2026: 1,695 stars14 Apr 2026: 1,713 stars21 Apr 2026: 1,741 stars28 Apr 2026: 1,759 stars5 May 2026: 1,771 stars12 May 2026: 1,788 stars19 May 2026: 1,801 stars26 May 2026: 1,817 stars2 Jun 2026: 1,830 stars9 Jun 2026: 1,838 stars16 Jun 2026: 1,847 stars23 Jun 2026: 1,855 stars30 Jun 2026: 1,866 stars7 Jul 2026: 1,876 stars14 Jul 2026: 1,886 stars21 Jul 2026: 1,890 stars28 Jul 2026: 1,898 stars4 Aug 2026: 1,905 stars11 Aug 2026: 1,910 stars18 Aug 2026: 1,916 stars25 Aug 2026: 1,925 stars1 Sept 2026: 1,933 stars8 Sept 2026: 1,938 stars15 Sept 2026: 1,945 stars22 Sept 2026: 1,946 stars29 Sept 2026: 1,949 stars6 Oct 2026: 1,952 stars13 Oct 2026: 1,957 stars20 Oct 2026: 1,964 stars

1,672 on 31 Mar 20261,964 on 20 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

TmuxAI runs inside a tmux window with a chat pane, an exec pane and read-only context panes. It captures visible pane content, sends it with chat history to a configured model, and runs suggested commands in the exec pane after confirmation. It also has watch mode, knowledge bases, skills, context squashing and MCP tool support.

Who it is for: Terminal-heavy developers who live in tmux and want an in-pane assistant

Strengths

  • Reads context from all panes in the tmux window, no copy-paste needed
  • Commands need confirmation unless whitelisted; blacklist patterns and risk indicator included
  • Prepare mode tracks exit codes and command completion for bash, zsh and fish
  • Knowledge bases and SKILL.md skills load context on demand; /squash trims history

Weaknesses

  • Requires tmux; targets Linux and macOS only
  • One TmuxAI instance per tmux window
  • Config lists openrouter, requesty, openai or azure; local models not documented
  • README says the command risk scoring is not exhaustive

What it needs

  • no GPU
  • Needs tmux, LLM API key (openrouter, requesty, openai or azure)
  • Models: openrouter, requesty, openai, azure

Also in Coding agents and AI editors

See all 143
Also in Coding agents and AI editors
RankProjectScore
1ArchonYAML workflow engine that runs AI coding agents through fixed dev steps23.7k starsMIT84 out of 100
2claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs195.1k starsMIT83 out of 100
3Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI11.1k starsMIT83 out of 100
#4piTerminal coding agent with extensions, skills, and an SDK117k starsMIT80 out of 100
#5oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory70.3k starscustom license80 out of 100