oh-my-openagent
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
What is oh-my-openagent?
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Overview of oh-my-openagent
What it is
OmO is an open-source command-line agent tool that turns tokens into finished work. It runs as a single omo command and is built on a fork of pi called senpi. The project is maintained as a personal side project by code-yeongyu.
Key features
- Ultrawork: Adding
ultraworkorulwto a prompt makes the agent read the codebase, plan, prove each step, check results on the real surface, and stop when done. - Mass ulw: Typing
mass ulwturns the whole job into a graph of agents that run in parallel, each on the model that fits it, with checks before anything is called done. - Kibitzer memory system: Memory lives in a git repository of markdown files. A small, cheap model sits beside the main agent, reads past work, and nudges the main agent to avoid repeating mistakes.
- Multi-model support: Users can mix frontier models with cheap ones.
/logincovers Claude, ChatGPT, Kimi and GLM subscriptions. Every model ships with a system prompt tuned for it. - Skills: OmO ships missing knowledge as skills, including browser use, and loads only what the task needs.
- Live reloading: Config, skills and prompts reload live. Independent tool calls run together in one small program. Malformed tool arguments are repaired before they run.
Use cases
OmO is designed for real work: research across ten thousand sources, creating presentations, building backends and frontends, writing code, running machine-learning pipelines, and performing migrations. It is used by professionals at companies including Indent, Google, Microsoft, Vercel, ELESTYLE, and Deepgram.
Getting started
bashcurl -fsSL https://get.omo.dev/install.sh | bashomoOn Windows, in PowerShell: irm https://get.omo.dev/install.ps1 | iex. The script installs the native omo binary into ~/.local/bin. Alternatively, install via npm: bun add -g omo-ai or npm i -g omo-ai. Open your project, run omo, describe the job.
License and pricing
The license is not stated in the provided metadata. The project is categorized as open source.
Based on the project's public README and repository metadata.