oh-my-openagent

OmO (Oh My OpenAgent) started as a plugin that supercharged OpenCode and Codex CLI and is now its own coding agent: one omo binary built on senpi, the team's fork of the pi agent. Add ultrawork to a prompt and it plans, routes subtasks to different models and keeps going until the job is done; mass ulw turns a job into a graph of agents.

Install with a curl script or bun add -g omo-ai (the unrelated omo package on npm belongs to someone else). It runs a shared background daemon and keeps config in ~/.omo. It can sign in with Claude, ChatGPT, Kimi or GLM subscriptions and ships built-in web search, docs lookup and a browser. The old OpenCode and Codex plugins still work but get degraded support from here on.

There's no paid tier; you pay for the models. But it isn't open source. The Sustainable Use License allows only internal business, non-commercial or personal use and bars commercial distribution or hosting. Solo devs experimenting with multi-model agents: fine. Companies building a product on it: no.

The catch: telemetry is on by default and reports token counts, cost and which models ran. Releases ship several times a day, and the marketing leans hard on grand claims. Anthropic's terms also bar third-party apps from offering Claude.ai login, which is what OmO's subscription sign-in does, so check before you rely on it.