Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Co-create PowerPoint slide decks with AI
| Date | Stars |
|---|---|
| 2026-07-24 | 362 |
| 2026-07-25 | 362 |
| 2026-07-28 | 362 |
| 2026-07-30 | 362 |
| 2026-08-06 | 362 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
---
title: SlideDeck AI
emoji: 🏢
colorFrom: yellow
colorTo: green
sdk: streamlit
sdk_version: 1.55.0
app_file: app.py
pinned: false
license: mit
---
[](https://pypi.org/project/slidedeckai/)
[](https://codecov.io/gh/barun-saha/slide-deck-ai)
[](https://slidedeckai.readthedocs.io/en/latest/?badge=latest)
[](https://opensource.org/licenses/MIT)
[](https://huggingface.co/spaces/barunsaha/slide-deck-ai)
# SlideDeck AI: The AI Assistant for Professional Presentations
We all spend countless hours **creating** slides and meticulously organizing our thoughts for any presentation.
**SlideDeck AI is your powerful AI assistant** for presentation generation. Co-create stunning, professional slide decks on any topic with the help of cutting-edge **Artificial Intelligence** and **Large Language Models**.
**The workflow is simple:** Describe your topic, and let SlideDeck AI generate a complete **PowerPoint slide deck** for you—it's that easy!
## Star History
[](https://star-history.com/#barun-saha/slide-deck-ai&Date)
## How It Works: The Automated Deck Generation Process
SlideDeck AI streamlines the creation process through the following steps:
1. **AI Content Generation:** Given a topic description, a Large Language Model (LLM) generates the *initial* slide content as structured JSON data based on a pre-defined schema.
2. **Visual Enhancement:** It uses keywords from the JSON output to search and download relevant images, which are added to the presentation with a certain probability.
3. **PPTX Assembly:** Subsequently, the powerful `python-pptx` library is used to generate the slides based on the structured JSON data. A user can choose from a set of pre-defined presentation templates.
4. **Refinement & Iteration:** At this stage onward, a user can provide additional instructions to *refine* the content (e.g., "add another slide," or "modify an existing slide"). A history of instructions is maintained for seamless iteration.
5. **Instant Download:** Every time SlideDeck AI generates a PowerPoint presentation, a download button is provided to instantly save the file.
In addition, SlideDeck AI can also create a presentation based on **PDF files**, transforming documents into decks!
## Python API Quickstart
<a target="_blank" href="https://colab.research.google.com/drive/1YA9EEmyiQFk03bOSc7lZnxK5l2hAL60l?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
```python
from slidedeckai.core import SlideDeckAI
slide_generator = SlideDeckAI(
model='[gg]gemini-2.5-flash-lite',
topic='Make a slide deck on AI',
api_key='your-google-api-key', # Or set via environment variable
)
pptx_path = slide_generator.generate()
print(f'🤖 Generated slide deck: {pptx_path}')
```
## CLI Usage
Generate a new slide deck:
```bash
slidedeckai generate --model '[gg]gemini-2.5-flash-lite' --topic 'Make a slide deck on AI' --api-key 'your-google-api-key'
```
Launch the Streamlit app:
```bash
slidedeckai launch
```
List supported models (these are the only models supported by SlideDeck AI):
```bash
slidedeckai --list-models
```
## Unmatched Flexibility: Choose Your AI Brain
SlideDeck AI stands out by supporting a wide array of LLMs from several online providers—Azure/ OpenAI, Google, SambaNova, Together AI, and OpenRouter. This gives you flexibility and control over your content generation style.
MoExcerpt of 13,638 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6343583c915b0272, topic:large-language-models, topic:llama
matched fp:6343583c915b0272, topic:streamlit