← Discover
GitHub · can1357/oh-my-pi

Artificial intelligence-supported coding in the terminal

Oh-my-pi is an artificial intelligence coding agent that runs in a terminal environment and automates code editing processes. The tool aims to optimize software development workflows with features such as language server protocol (LSP), browser integration, and subagent management.

Updates

  • November 8, 2026: Stars 38,069 → 38,170, latest release v18.18.1 (November 8, 2026).
  • November 7, 2026: Stars 37,973 → 38,069, latest release v18.18.0 (November 7, 2026).
  • November 6, 2026: Stars 37,576 → 37,973, latest release v18.17.0 (November 6, 2026).
  • November 3, 2026: Stars 37,480 → 37,576, latest release v18.16.0 (November 2, 2026).

What you get

  • It automates code editing processes by bringing IDE features to the terminal.
  • With LSP integration, it performs operations such as renaming and reference tracking without any errors.
  • It resolves issues on-site by interacting directly with debugging tools.

Installation

Installation for macOS and Linux
curl -fsSL https://omp.sh/install | sh
Installation via this
bun install -g @oh-my-pi/pi-coding-agent

Running it

Configuring shell complements
# zsh — add to ~/.zshrc (or write the output into a file on your $fpath)
eval "$(omp completions zsh)"

# bash — add to ~/.bashrc
eval "$(omp completions bash)"

# fish
omp completions fish > ~/.config/fish/completions/omp.fish

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I started using the Oh My Pi tool on my terminal. How can I optimize my workflow by using advanced features such as LSP support, debugging, and subagent management in my projects with this AI coding agent? Explain step by step how to use the built-in tools this tool offers in the most efficient way, especially in code editing, file reading and debugging.

Repository: https://github.com/can1357/oh-my-pi. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

LSPAI Coding AgentCoding AgentIDETerminalAgent
Who it is forIt is suitable for software developers who want to automate their code development processes via the terminal and speed up the workflow with an artificial intelligence-supported coding agent.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-02: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.