// Multimodal AI processing and image generation using Google Gemini. Use for analyzing PDFs, images, videos, YouTube links, and other large documents. Also generates images with Nano Banana Pro. Ideal when you need to extract information from files that require vision or multimodal understanding, or generate images from text prompts.
| name | gem |
| description | Multimodal AI processing and image generation using Google Gemini. Use for analyzing PDFs, images, videos, YouTube links, and other large documents. Also generates images with Nano Banana Pro. Ideal when you need to extract information from files that require vision or multimodal understanding, or generate images from text prompts. |
Use the ai-gem CLI tool for multimodal AI processing and image generation via Google's Gemini API.
# Text queries
ai-gem "Write a haiku about Python programming"
# Analyze documents
ai-gem "Summarize this document" document.pdf
# Analyze images
ai-gem "What's in this image?" photo.jpg
# Process YouTube videos
ai-gem "Create a 5-point summary" "https://youtu.be/VIDEO_ID"
# Compare multiple files
ai-gem "Compare these files" file1.pdf file2.png
# Web search
ai-gem "Current AI news" --search
# Generate images (uses Nano Banana Pro by default)
ai-gem --image "A cute robot reading a book in a cozy library"
ai-gem --image "A landscape at sunset" --aspect-ratio 16:9
ai-gem --image "A cat wearing a hat" -o cat.png
ai-gem --image "Edit this to add sunglasses" reference.jpg
# Use alternative image model
ai-gem --image "A blue triangle" -m gemini-2.5-flash-image
--image / -i: Generate an image instead of text--output / -o: Output file path (auto-generated if omitted)--aspect-ratio / -a: Aspect ratio (1:1, 9:16, 16:9, etc.)--model / -m: Override model (default: nano-banana-pro-preview)GEMINI_API_KEY environment variable must be sethamel package must be installed: pip install hamelManage your YouTube channel — upload, list, edit metadata, schedule/unschedule videos, set thumbnails, download your own private videos, get transcripts, generate AI chapter summaries, and post comments (with a Chrome-automation playbook for pinning). Use when asked to upload to YouTube, schedule a video, edit video metadata, download a private YouTube video, get a transcript, generate chapters, or post/pin a comment.
Unified X (Twitter) CLI — fetch follows, diff snapshots, get likes/bookmarks, fetch latest posts, and take screenshots. Uses the official X API v2 with Bearer Token and OAuth 2.0 user-context auth.
Create annotated blog posts from technical talks with slides. Use when asked to convert a video presentation to a blog post, create written content from a talk, or annotate slides with transcript.
Fetch Kit (ConvertKit) newsletter broadcasts for writing context. Use when asked to download newsletters, get past email content for style reference, or fetch broadcasts for analysis.