# oh-my-pi: Coding Agent Built on Mario Zechner’s Pi This repository profile is provided by osrepos.com, an open source repository discovery platform. Source: osrepos.com Repository profile: https://osrepos.com/repo/can1357-oh-my-pi Generated for open source discovery and AI-assisted research. 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 OSRepos URL: https://osrepos.com/repo/can1357-oh-my-pi ## 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. ## Topics - typescript - ai-agents - coding-agent - terminal - multi-provider - language-server - debugger ## Repository Information Last analyzed by OSRepos: Wed Oct 21 2026 22:05:32 GMT+0100 (Western European Summer Time) Detail views: 1 GitHub clicks: 0 ## Safety Notice OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything. ## Content ## Overview oh-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. The 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. ## Key Features - IDE integration through language-server operations for diagnostics, navigation, renames, and code actions. - Debugging through the Debug Adapter Protocol, with support for breakpoints, stepping, and inspecting variables. - Persistent Python and JavaScript execution, with the ability to call agent tools from the execution environment. - Parallel subagents, including isolated worktrees and structured results. - A native tool surface for reading, searching, editing, and working with files, URLs, and repository-related internal paths. - Multiple interfaces: terminal UI, one-shot prompts, a Node/TypeScript SDK, stdio RPC, and Agent Client Protocol for editors. - Broad model and provider routing, with configurable roles, custom OpenAI-compatible providers, and fallback chains. - Cross-platform native components and an embedded shell intended to avoid external-process calls for many common operations. ## Use Cases - A developer wants a terminal-based agent that can use LSP features and make safer, IDE-aware changes across a codebase. - A team needs an agent to investigate bugs with a real debugger instead of relying only on added print statements. - A TypeScript application wants to embed an agent session through the project’s SDK or control one over RPC. - A developer wants to split independent repository tasks among subagents and review their structured findings. - A user needs one coding-agent workflow across macOS, Linux, and Windows, with configurable model providers. ## Our Take Active 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. **Good fit if:** - You want a terminal-first coding agent built on Pi with LSP, debugger, and code-execution tools integrated into its workflow. - You value configurable providers, subagents, and multiple integration surfaces, including an SDK and editor protocol. - You can work with its TypeScript and Rust stack and are comfortable adopting a project that is actively evolving. **Look elsewhere if:** - You need a minimal agent with a narrow toolset rather than a broad, configurable coding environment. - Your deployment cannot accommodate the project’s Rust native components or its Bun-oriented installation and development workflow. - You need a stable, fixed feature surface and do not want to track an actively developed project. ## Project Health | Signal | Value | |---|---| | Status | **Active**: regular commits and releases | | Last commit | 2026-10-21 (today) | | Commits, last 90 days | 100+ | | Releases, last 12 months | 100+ (latest v18.12.6, 2026-10-21) | | Contributors | 100+ (top contributor: 48% of commits) | | Issues closed, last 90 days | 12+ (typically closed in 0 days) | | Pull requests merged, last 90 days | 86 (typically merged in 1 day) | | Project age | 10 months | Checked on 2026-10-21 with the GitHub API. ## Project Facts - Language: TypeScript - License: MIT - Stars: 36.2k - Forks: 4k - Topics: ai-agent, ai-coding-agent, anthropic, bun, claude, cli, coding-assistant, llm - Website: https://omp.sh - Archived: no ## What You Need Detected in the repository: - Node.js (from package.json) - Rust (from Cargo.toml) - A Dockerfile, so it can run in a container - Automated checks on GitHub Actions ## Getting Started Install on macOS or Linux with: ```sh curl -fsSL https://omp.sh/install | sh ``` For Windows, Bun, Homebrew, Nix, pinned versions, and configuration details, see the [README](https://github.com/can1357/oh-my-pi#readme). ## License in Plain Words **MIT** (permissive). - Commercial use: yes - Modify and redistribute: yes - You must keep: the copyright and license notice - Share your changes: no A summary, not legal advice: the LICENSE file is what applies. ## Alternatives - [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. - [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. - [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. - [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. | Project | Language | License | Stars | Status | |---|---|---|---|---| | **oh-my-pi** | TypeScript | MIT | 36.2k | Active | | [openinterpreter](https://osrepos.com/repo/openinterpreter-openinterpreter) | Rust | Apache-2.0 | 68.5k | Active | | [tau](https://osrepos.com/repo/huggingface-tau) | Python | MIT | 3k | New | | [fx](https://osrepos.com/repo/vercel-labs-fx) | Zig | Apache-2.0 | 3.3k | New | | [zero](https://osrepos.com/repo/gitlawb-zero) | Go | MIT | 1.7k | New | ## Considerations - The project combines TypeScript with Rust native components, so building from source involves both workspace dependencies and a local native-addon build. - 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. - The repository is actively changing, with frequent commits and releases. That supports momentum but means behavior and interfaces may evolve. - 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. - The README reports no test-suite status in the supplied repository requirements data, so teams should verify the checks that cover their intended workflows.