{"name":"oh-my-pi: Coding Agent Built on Mario Zechner’s Pi","description":"oh-my-pi is a terminal-first coding agent and IDE-aware fork of Mario Zechner’s Pi, with built-in code tools, subagents, and editor integration. It runs on macOS, Linux, and Windows, and can also be embedded as a TypeScript SDK.","github":"https://github.com/can1357/oh-my-pi","url":"https://osrepos.com/repo/can1357-oh-my-pi","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/can1357-oh-my-pi","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/can1357-oh-my-pi.md","json":"https://osrepos.com/repo/can1357-oh-my-pi.json","topics":["typescript","ai-agents","coding-agent","terminal","multi-provider","language-server","debugger"],"keywords":["typescript","ai-agents","coding-agent","terminal","multi-provider","language-server","debugger"],"stars":null,"summary":"oh-my-pi is a terminal-first coding agent and IDE-aware fork of Mario Zechner’s Pi, with built-in code tools, subagents, and editor integration. It runs on macOS, Linux, and Windows, and can also be embedded as a TypeScript SDK.","content":"## Overview\n\noh-my-pi (omp) is a terminal-first coding agent built as a coding-focused fork of [Pi](https://github.com/badlogic/pi-mono) by Mario Zechner. It aims to give the agent IDE-like capabilities, including language-server operations, debugging, code execution, and structured file editing, rather than relying only on shell commands and text generation.\n\nThe project combines a TypeScript agent and CLI with a substantial Rust native core. It supports macOS, Linux, and Windows, and offers interactive terminal, one-shot, SDK, RPC, and editor-facing ACP entry points. Its breadth makes it most relevant to developers who want an extensible, model-flexible agent for real repository work.\n\n## Key Features\n- IDE integration through language-server operations for diagnostics, navigation, renames, and code actions.\n- Debugging through the Debug Adapter Protocol, with support for breakpoints, stepping, and inspecting variables.\n- Persistent Python and JavaScript execution, with the ability to call agent tools from the execution environment.\n- Parallel subagents, including isolated worktrees and structured results.\n- A native tool surface for reading, searching, editing, and working with files, URLs, and repository-related internal paths.\n- Multiple interfaces: terminal UI, one-shot prompts, a Node/TypeScript SDK, stdio RPC, and Agent Client Protocol for editors.\n- Broad model and provider routing, with configurable roles, custom OpenAI-compatible providers, and fallback chains.\n- Cross-platform native components and an embedded shell intended to avoid external-process calls for many common operations.\n\n## Use Cases\n- A developer wants a terminal-based agent that can use LSP features and make safer, IDE-aware changes across a codebase.\n- A team needs an agent to investigate bugs with a real debugger instead of relying only on added print statements.\n- A TypeScript application wants to embed an agent session through the project’s SDK or control one over RPC.\n- A developer wants to split independent repository tasks among subagents and review their structured findings.\n- A user needs one coding-agent workflow across macOS, Linux, and Windows, with configurable model providers.\n\n## Our Take\nActive development, frequent releases, broad contributor participation, and quick PR merges make omp a fast-moving option for developers who want an unusually integrated coding-agent workflow.\n\n**Good fit if:**\n- You want a terminal-first coding agent built on Pi with LSP, debugger, and code-execution tools integrated into its workflow.\n- You value configurable providers, subagents, and multiple integration surfaces, including an SDK and editor protocol.\n- You can work with its TypeScript and Rust stack and are comfortable adopting a project that is actively evolving.\n\n**Look elsewhere if:**\n- You need a minimal agent with a narrow toolset rather than a broad, configurable coding environment.\n- Your deployment cannot accommodate the project’s Rust native components or its Bun-oriented installation and development workflow.\n- You need a stable, fixed feature surface and do not want to track an actively developed project.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **Active**: regular commits and releases |\n| Last commit | 2026-10-21 (today) |\n| Commits, last 90 days | 100+ |\n| Releases, last 12 months | 100+ (latest v18.12.6, 2026-10-21) |\n| Contributors | 100+ (top contributor: 48% of commits) |\n| Issues closed, last 90 days | 12+ (typically closed in 0 days) |\n| Pull requests merged, last 90 days | 86 (typically merged in 1 day) |\n| Project age | 10 months |\n\nChecked on 2026-10-21 with the GitHub API.\n\n## Project Facts\n\n- Language: TypeScript\n- License: MIT\n- Stars: 36.2k\n- Forks: 4k\n- Topics: ai-agent, ai-coding-agent, anthropic, bun, claude, cli, coding-assistant, llm\n- Website: https://omp.sh\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Node.js (from package.json)\n- Rust (from Cargo.toml)\n- A Dockerfile, so it can run in a container\n- Automated checks on GitHub Actions\n\n## Getting Started\nInstall on macOS or Linux with:\n\n```sh\ncurl -fsSL https://omp.sh/install | sh\n```\n\nFor Windows, Bun, Homebrew, Nix, pinned versions, and configuration details, see the [README](https://github.com/can1357/oh-my-pi#readme).\n\n## License in Plain Words\n\n**MIT** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the copyright and license notice\n- Share your changes: no\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [openinterpreter](https://osrepos.com/repo/openinterpreter-openinterpreter): Open Interpreter is Rust-based and targets low-cost models, with support for multiple agent harnesses and ACP-compatible editors.\n- [tau](https://osrepos.com/repo/huggingface-tau): Tau is a Python teaching-focused port of Pi, while oh-my-pi adds IDE integration, subagents, and built-in code tools.\n- [fx](https://osrepos.com/repo/vercel-labs-fx): fx is a native Zig agent CLI with an interactive shell and embedding options, rather than an IDE-aware TypeScript fork of Pi.\n- [zero](https://osrepos.com/repo/gitlawb-zero): Zero is a Go-based agent focused on scriptable assistance, local sessions, and explicit controls over side effects.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **oh-my-pi** | TypeScript | MIT | 36.2k | Active |\n| [openinterpreter](https://osrepos.com/repo/openinterpreter-openinterpreter) | Rust | Apache-2.0 | 68.5k | Active |\n| [tau](https://osrepos.com/repo/huggingface-tau) | Python | MIT | 3k | New |\n| [fx](https://osrepos.com/repo/vercel-labs-fx) | Zig | Apache-2.0 | 3.3k | New |\n| [zero](https://osrepos.com/repo/gitlawb-zero) | Go | MIT | 1.7k | New |\n\n## Considerations\n- The project combines TypeScript with Rust native components, so building from source involves both workspace dependencies and a local native-addon build.\n- Its many tools, providers, settings, and integration modes add configuration surface area; teams should review the project’s trust and project-input behavior before enabling it in unfamiliar repositories.\n- The repository is actively changing, with frequent commits and releases. That supports momentum but means behavior and interfaces may evolve.\n- The measured contributor base is broad rather than concentrated around one person. Recent pull requests are merged quickly, though this does not by itself establish long-term support guarantees.\n- The README reports no test-suite status in the supplied repository requirements data, so teams should verify the checks that cover their intended workflows.","metrics":{"detailViews":1,"githubClicks":0},"dates":{"published":null,"modified":"2026-10-21T21:05:32.000Z"}}