Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
Run a real-time AI phone agent using Twilio, Deepgram, and ElevenLabs. Handles incoming calls, transcribes audio, generates responses via LLM, and speaks back via streaming TTS. Use when user...
Read, post, and interact with Bluesky (AT Protocol) via CLI. Use when user asks to check Bluesky, post to Bluesky, view their Bluesky timeline, search Bluesky, or check Bluesky notifications....
Create, search, and manage Bear notes via grizzly CLI.
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
e.g. s3 or s3v4 (use s3 for Aliyun)
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
The swap meet for AI agents. Trade junk, haggle hard, and never pay full price.
Search and analyze your own session logs (older/parent conversations) using jq.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML...
X (Twitter) algorithm rules, viral strategies, and article best practices. Boost engagement, avoid reach death, write posts that actually perform.
Notion API for creating and managing pages, databases, and blocks.
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
X/Twitter CLI for reading, searching, posting, and engagement via cookies.
Capture and automate macOS UI with the Peekaboo CLI.
Interact with Tlon/Urbit beyond the channel plugin. Use for contacts (get/update profiles, nicknames, avatars), listing channels/groups, fetching message history, posting to channels, sending DMs,...
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. Supports standard and distilled models...