media-gen renders Claude-authored content — SVG markup, HTML documents, or a JavaScript canvas draw() function — into PNG/JPEG/WebP images and MP4 video using headless Chromium and ffmpeg, with no API keys required. It also offers an optional bring-your-own-key path for photorealistic text-to-image and text-to-video generation via OpenAI, Gemini, or fal.ai.
Enables users to manage Sonarr and Radarr instances through natural language, allowing search, addition, deletion, and monitoring of TV series and movies.
Enables searching and downloading images, videos, and multi-image galleries from e621, rule34, E-Hentai/ExHentai, and Pixiv, with support for batch downloads, URL-based retrieval, and optional animation conversion to GIF/MP4.
Enables finding information online, reading web pages, finding images, capturing screenshots, and performing multi-source research with per-answer confidence.
Enables AI agents and their users to retrieve scored news sentiment, narratives, historical readings, and cited sources for Bitcoin, gold, and oil, with tamper-evident, time-stamped data for trading decisions.
Checks a social post against a platform's real character limit before it ships — X bills every URL at 23 characters and weights non-Latin script at 2, while Bluesky and Mastodon count grapheme clusters. Covers X, X Premium, Bluesky, LinkedIn, Threads, Mastodon, and Discord, with no credentials and no network access.
Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.
Provides a unified web search tool for AI agents by running multiple search providers concurrently and returning normalized results. It integrates with Claude Code, Codex CLI, OpenCode, and Hermes.