Sandbox
@oomol-lab/oo-cli

CLI connector for OOMOL services and agent skills

oo is a CLI that sits between your agent and OOMOL's hosted capabilities, plus the third-party accounts you connect in OOMOL Console. It lets the agent discover, inspect, and call those capabilities from the terminal, and it comes with bundled skills that tell supported hosts how to use it.

40 stars6 forksTypeScriptUpdated 9d ago
Who it's for

Builders who want their agent to act on connected accounts and hosted pipelines from the terminal.

What it delivers

You can ask your agent to handle connected apps and hosted tasks without switching tools or re-entering credentials.

What it does

Connected account access

Links a machine to an OOMOL account with `oo login`, then lets agents use connected services like Gmail, Calendar, Drive, Notion, Slack, and GitHub.

Hosted capabilities

Exposes OOMOL-managed pipelines for OCR, translation, transcription, text-to-speech, text-to-image, subtitling, and long-document understanding.

Bundled agent skills

Installs skills into supported agent hosts so they know when and how to route requests through `oo`.

Self-hosted connector support

Documents how to set up and use the self-hosted connector integration for local or private deployments.

How to get it

  1. 1macOS / Linux
    curl -fsSL https://cli.oomol.com/install.sh | bash
  2. 2Windows PowerShell
    irm https://cli.oomol.com/install.ps1 | iex
  3. 3Run
    oo login

README

oo

oo

Plug AI agents into OOMOL's hosted capabilities and your connected accounts.

Release Publish License Console

English · 简体中文


What is oo?

oo is the CLI that lets AI agents on your machine discover, inspect, and call OOMOL's hosted capabilities and the third-party services you've already connected.

Two kinds of capabilities are reachable through oo:

  • Connected accounts — third-party services you authorize once in the OOMOL Console (Gmail, Google Calendar, Google Drive, Notion, Slack, GitHub, and more). Once a service is connected, your AI agent can act on it through oo without re-authenticating.
  • Hosted capabilities — managed AI pipelines such as OCR, translation, transcription, text-to-speech, text-to-image, subtitling, and long-document understanding.

You don't memorize commands. The bundled skills teach supported AI agents when and how to route out-of-workspace work through oo.

How it works

  1. Install oo on this machine.
  2. Run oo login to link this machine to your OOMOL account.
  3. Connect services at https://console.oomol.com/connections, then ask your AI agent — the bundled oo skill tells it when and how to call the right capability.

Install

macOS / Linux:

curl -fsSL https://cli.oomol.com/install.sh | bash

Windows PowerShell:

irm https://cli.oomol.com/install.ps1 | iex

Other install scripts (wget, Windows CMD, etc.) are listed at https://cli.oomol.com/install-guide.md.

Quick start

oo login

Then talk to your AI agent in natural language — describe intent, not commands:

/oo summarize my latest 5 Gmail messages.

/oo is the prompt convention picked up by the bundled skill; the agent will route the request through oo for you.

Supported AI agents

On first launch, oo installs bundled skills into any of the following AI agent hosts that already exist on this machine: Codex, Claude Code, Hermes, CodeBuddy, WorkBuddy, Trae, Trae CN, OpenClaw, QoderWork, and DeepSeek TUI.

Bundled skills are kept in sync with each oo release. See the command reference for the exact skill targets and how to manage them manually.

Agents may use a bundled skill on their own when a request matches it. To make them wait until you ask by name, run oo skills auto-trigger off --all (or name individual skills). The skills stay installed and invocable — /oo in Claude Code, $oo in Codex.

Privacy

oo records privacy-constrained telemetry by default. Events do not include free-form input text, paths, usernames, hostnames, IP addresses, real OOMOL account ids, or account names. Telemetry controls and the full boundary are documented in PRIVACY.md.

Links

Files in the repo

Repository payload30 top-level entries
  • __tests__
  • .github
  • .vscode
  • contrib
  • docs
  • src
  • .bun-version
  • .editorconfig
  • .gitattributes
  • .gitignore
  • AGENTS.md
  • bun.lock
  • bunfig.toml
  • CLAUDE.md
  • CODE_QUALITY_RULES.md
  • CONTRIBUTING.md
  • cspell.config.yml
  • eslint.config.js
  • eslint.config.test.ts
  • index.ts
  • knip.json
  • LICENSE
  • oo
  • oo.bat
  • package.json
  • PRIVACY-ZH_CN.md
  • PRIVACY.md
  • README-ZH_CN.md
  • README.md
  • tsconfig.json

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k