# OmO

> Terminal coding agent run through the omo command. It runs on senpi, a fork of pi, and can split a job into parallel agents across multiple models.

Stars: 70.4k · Language: TypeScript · Categories: AI

- Repository: https://github.com/code-yeongyu/oh-my-openagent
- Website: https://omo.dev
- Page: https://www.trmn.sh/tools/oh-my-openagent

## Install

- Shell script: `curl -fsSL https://get.omo.dev/install.sh | bash`
- Bun: `bun add -g omo-ai`
- npm: `npm i -g omo-ai`

## Overview

OmO is a terminal AI coding agent launched with the `omo` command. You open a project, run `omo`, and describe the job. It runs on senpi, a fork of pi (badlogic/pi-mono), and is distributed as a native binary for Linux/macOS and Windows. Its tasks include research, backend and frontend work, and general coding.

Adding `ultrawork` (or `ulw`) to a prompt makes the agent read the codebase first, plan, verify each step, and check the result before stopping. Typing `mass ulw` turns the job into a graph of agents. Each part runs in parallel on a model chosen for it, and the results are checked before the job is reported done. The README gives deep research and migrations as example uses.

Other documented features include Kibitzer, a memory system stored as markdown files in a git repository. A small, cheap model runs beside the main agent and nudges it based on your past behavior. `/login` supports Claude, ChatGPT, Kimi and GLM subscriptions. Each model gets its own system prompt. Skills, including browser use, are loaded only when a task needs them. Independent tool calls run together in one small program. Malformed tool arguments are repaired before they run. Long-running work keeps a record of what was checked, so a restarted session can resume. Config, skills and prompts reload live.

Configuration lives in `~/.omo/omo.jsonc`, and a project can add `.omo/omo.jsonc`, with the closest file winning. Users of the earlier OpenCode edition or LazyCodex can run `omo setup` to carry over provider keys, MCP servers, skills and model picks. `omo doctor` then reports which task categories the configured providers can run. The tool is aimed at developers who want to run long, multi-step engineering tasks across several model providers.

### Installation

```bash
# via Shell script
curl -fsSL https://get.omo.dev/install.sh | bash
```

```bash
# via Bun
bun add -g omo-ai
```

```bash
# via npm
npm i -g omo-ai
```

![OmO workflow DAG in a Herdr side pane](https://media.trmn.sh/cached/9353ee86ff1f08fd446de11db0e88834f6c947125ef43e21c94d3574efed2e74.png)

## Alternatives

- [oh-my-pi](https://www.trmn.sh/tools/oh-my-pi.md): Terminal coding agent (fork of Pi) with LSP and DAP debugger integration, subagents, Python/Bun execution, and in-process native tools. Supports 60+ providers. (TypeScript, 37.0k stars)
- [Continue](https://www.trmn.sh/tools/continue.md): Open-source coding agent distributed as a CLI, VS Code extension, and JetBrains plugin. Repository is read-only after the final 2.0.0 release. (TypeScript, 36.4k stars)
- [OpenClaude](https://www.trmn.sh/tools/openclaude.md): Open-source terminal coding-agent CLI that works with OpenAI-compatible APIs, Gemini, GitHub Models, Codex, Ollama and other cloud or local model backends. (TypeScript, 34.2k stars)
- [gemini-cli](https://www.trmn.sh/tools/gemini-cli.md): Terminal AI agent providing direct command line access to Google Gemini models with file operations, web search, and tool integration. (TypeScript, 108.6k stars)
- [Qwen Code](https://www.trmn.sh/tools/qwen-code.md): Open-source AI coding agent that runs in the terminal, with IDE plugins, desktop app, SDKs, and multi-provider model support (OpenAI, Anthropic, Gemini, Qwen). (TypeScript, 28.8k stars)

---

Canonical: https://www.trmn.sh/tools/oh-my-openagent