rem for Openclaw

A high-performance Go-based CLI for macOS Reminders that enables fast task management via the terminal or AI agents.

bro3886
v1.0.0
Feb 28, 2026
0
1.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install rem-cli

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install rem-cli using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is rem?

rem is a powerful command-line interface designed for macOS users who want to interact with the native Reminders application without leaving the terminal. Built with Go and utilizing cgo to interface directly with the EventKit framework, it offers sub-200ms read times and a robust set of features including natural language processing for dates. This tool transforms a GUI-bound utility into a scriptable, developer-friendly interface.

By adding this tool to your repertoire of Openclaw Skills, you can bridge the gap between AI-driven workflows and system-level task management. Whether you are automating your daily stand-up tasks or building complex productivity scripts, rem provides the reliability and speed needed for professional-grade automation on macOS.

rem Use Cases

  • Automating the creation of reminders directly from build scripts or terminal-based workflows.
  • Integrating native macOS tasks into AI agent routines using Openclaw Skills.
  • Rapidly adding tasks with natural language dates like "tomorrow at 3pm" or "next friday".
  • Exporting reminder data to JSON or CSV for data analysis or third-party tool synchronization.
  • Performing batch operations on reminders, such as bulk-completing tasks or searching across all lists.

How rem Works

  1. The user enters a command using the rem CLI or triggers a request through an AI agent.
  2. The CLI parses natural language date inputs and flags to determine the intent (CRUD operations).
  3. rem communicates with the macOS Reminders database via the EventKit framework and cgo for maximum performance.
  4. For specialized attributes like flags, the tool utilizes JXA (Javascript for Automation) as a fallback mechanism.
  5. The requested data is returned to the user in the specified output format, such as a formatted table or machine-readable JSON.

rem Setup

To install rem on your macOS system, run the following command in your terminal:

curl -fsSL https://rem.sidv.dev/install | bash

Once installed, you can integrate it with your AI agent to expand your Openclaw Skills library:

rem skills install --agent openclaw

Note: You must grant the terminal or agent permissions to access Reminders under macOS System Settings > Privacy & Security.

rem Data Schema & Taxonomy

rem organizes reminders and lists using the native macOS EventKit schema, supplemented by short identifiers for CLI efficiency.

Property Description Supported Formats
Short ID The first 8 characters of the reminder UUID String (e.g., abc12345)
List The category or list name in Reminders.app String
Due Date Scheduled deadline for the task Natural Language / ISO
Priority Task importance level high, medium, low, none
Output Data rendering format table, json, plain
Metadata Internal storage for URLs and notes String

rem Advanced Features

  • Natural Language Support: Parse complex time strings like "in 3 hours" or "eod" automatically.
  • Machine-Readable Exports: Full support for JSON and CSV output formats for use in pipeline scripting.
  • Interactive Mode: Use rem interactive for a guided terminal UI experience.
  • Smart Search: Search through titles and notes across all reminder lists simultaneously.
  • Short ID Referencing: Interact with specific reminders using unique prefix-based IDs for faster command entry.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*