oh-my-pi
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
claude mcp add --transport stdio can1357-oh-my-pi npx -y @oh-my-pi/pi-coding-agent
How to use
oh-my-pi is an AI coding agent designed to run in your terminal. It provides a range of tools to help you write, review, and manage code more efficiently, including a Commit Tool for AI-assisted git commits, a persistent Python tool with an IPython kernel, LSP-based code intelligence, a Time Traveling Streamed Rules (TTSR) feature for zero-context injections, and an Interactive Code Review workflow. To start using it, run the MCP server via its npm package (for example with npx as shown in the configuration). Once started, you can invoke the agent's capabilities through its command surface and built-in commands, such as committing code with intelligent analysis, executing Python snippets in a persistent kernel, or invoking the code-review workflow to generate structured findings and verdicts. The included Tools section outlines the available capabilities you can exercise, including Slash Commands, Editor Features, and the Task Tool, each designed to streamline development tasks inside the terminal environment.
How to install
Prerequisites:
- Node.js (≥ 14 or later) and npm/yarn installed on your system
- Internet access to fetch the MCP server package
Installation steps:
-
Ensure Node.js and npm are available
- node -v
- npm -v
-
Install or run the MCP server via npx (recommended for quick start)
- npx -y @oh-my-pi/pi-coding-agent
-
Optional: Install globally for repeated use
- npm install -g @oh-my-pi/pi-coding-agent
- pi-coding-agent
-
If you prefer to pin a specific version, use a version specifier with npx or npm install accordingly. After installation, follow any on-screen prompts to authenticate or configure API keys if required by the agent’s features.
Note: The repository’s README indicates the npm package @oh-my-pi/pi-coding-agent as the primary delivery artifact.
Additional notes
Tips and common issues:
- If using npx, ensure your npm cache is up to date to avoid fetch errors.
- Some features may require API keys or environment configurations (not shown in the README); consult the project’s documentation for any required credentials.
- When using globally installed versions, keep them up to date to receive latest capabilities and fixes.
- If you encounter network or permission issues, try running with elevated privileges or adjust npm's registry/mirror settings.
- The agent integrates with a variety of tools (e.g., Commit Tool, Python tool, LSP, and Task Tool); ensure the terminal supports the rendering needs for rich outputs (images, Mermaid diagrams, etc.).
Related MCP Servers
claude-code-open
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
mcp -atlassian-bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
local-skills
Universal MCP server enabling any LLM or AI agent to utilize expert skills from your local filesystem. Reduces context consumption through lazy loading. Works with Claude, Cline, and any MCP-compatible client.
mcp-client-gen
Turn any MCP server into a type-safe TypeScript SDK in seconds - with OAuth 2.1 and multi-provider support
mcp-interactive-terminal
MCP server that gives AI agents (Claude Code, Cursor, Windsurf) real interactive terminal sessions — REPLs, SSH, databases, Docker, and any interactive CLI with clean output and smart completion detection
nucleus
The Sovereign Agent Control Plane — One brain for Cursor, Claude, and Windsurf.