MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It fills a narrow but real gap in AI slide-deck automation by providing run-scoped temporary image hosting with automatic cleanup, rather than acting as yet another persistent file store.
Who it is for
- People building AI-assisted slide decks through NotebookLM-to-Canva automation
- Users who need temporary hosting of slide images during presentation runs
- Developers or workflow designers integrating Canva with AI-generated slide assets
- Static-site users looking for a lightweight web-based staging utility
Use cases
- Stage slide images for an active NotebookLM-to-Canva presentation run
- Upload run-specific slide decks and have them cleaned up after Canva ingestion
- Temporarily serve generated slide images to Canva through a web interface
- Validate a short-lived staging step in an automated slide-deck pipeline
Strengths
- Run-scoped uploads prevent mixing files across presentation runs
- Automatic cleanup after Canva ingestion keeps staging area focused on the current run
- Simple web-based interface requires only HTML and static hosting
- Explicitly avoids persistent storage, making privacy and cleanup behavior clear
Considerations
- Not designed for permanent storage or archival of slide images
- No dedicated configuration format documented beyond deployment and runtime
- Requires a web server or static host, network access, and NotebookLM/Canva workflow access
- Provides staging only; actual automation logic must live outside the tool
README quick start
Getting Started
Description
AI Slide Deck Automation 2026 is a browser-based staging utility for NotebookLM-to-Canva presentation workflows, temporarily serving slide images and clearing each run's files after ingestion is complete.
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.