Organize and Edit text, images, and videos on a freeform canvas.
Run AI models on your content (using your own API keys) and then
combine it all into LLM-generated inline HTML pages.
This project has been 100% coded by Claude Code,
under the careful guidance
of rms80,
an independent software developer.
Drop anything onto a boundless workspace and arrange it however you want.
Editable text blocks with auto-sizing. Double-click to edit, arrange freely on the canvas.
Drag-and-drop or paste from clipboard. Non-destructive server-side crop editing.
Drop video files with full playback controls. Trim, crop, change speed, and remove audio.
AI-generated HTML rendered in sandboxed iframes. Full web pages, live on your canvas.
Configurable prompt blocks that generate content inline. Select canvas items as context for your prompts.
Pan, zoom, and arrange without limits. Marquee selection, multi-select, and free-form positioning.
Generate text, images, and entire web pages directly on the canvas using leading AI models.
Create prompt blocks and generate text with Claude (Haiku, Sonnet, Opus) or Google Gemini (Flash, Pro). Select items on the canvas as context.
Generate images using Gemini Imagen models. Describe what you need and the image appears right on your canvas.
Generate full, interactive HTML pages from selected canvas content. The AI understands the spatial layout of your workspace.
Three deployment modes to fit your workflow.
Cloud storage with AWS S3 via the backend server. Full feature set with remote access.
Store scenes on your local filesystem via the local server. Your data stays on your machine.
Fully client-side using IndexedDB. No backend needed. Configure your own API keys for AI features.
A robust, type-safe stack for both frontend and backend.
gsworkspace is open source and free to use. Clone the repo and start building.
git clone https://github.com/rms80/gsworkspace.git