# Awesome Gemini API examples

Here's a list of really cool Gemini-powered projects, demos and hacks that we liked. We hope that they will give you some ideas on what to build with Gemini next.

You should also have a look at our Google-maintained [quickstarts](quickstarts/) and [examples](examples/).

## Gemini API-powered projects

Those projects are ordered in an anti-chronological order and are the work of their authors, who are are not necessarily affiliated with Google.

### Creating workflows diagrams using Gemini

From [Gitesh Mahadik](https://medium.com/@gitesh08), Create amazing workflows diagrams for your next pack of slides: https://medium.com/google-cloud/how-to-generate-workflow-diagrams-using-gemini-8d3d538bd2e7

### [Caching] Helping with navigating a lot of documentation 

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">The context caching feature for Gemini is really neat!<br><br>As you all know, I write a lot and document AI research progress in lots of places. But I also tend to forget research findings due to the vast amount of papers I read so I wanted to try whether context caching can help me… <a href="https://t.co/7Q7G2RapFD">pic.twitter.com/7Q7G2RapFD</a></p>&mdash; elvis (@omarsar0) <a href="https://twitter.com/omarsar0/status/1803171489446785354?ref_src=twsrc%5Etfw">June 18, 2024</a></blockquote>


### [Vision + Math reasoning] Solving Math problems on a white board

Gemini analyze the math drawn then computes an answers as well as where to display it. It can even recognize variables, functions, and solve brain teasers.

![Solving Math problems in tldraw](https://pbs.twimg.com/media/GP818DAWUAEkZSA?format=jpg&name=900x900)

<blockquote class="twitter-tweet" data-media-max-width="560"><p lang="en" dir="ltr">finally we can do maths <a href="https://t.co/SoECzN1Aom">pic.twitter.com/SoECzN1Aom</a></p>&mdash; tldraw (@tldraw) <a href="https://twitter.com/tldraw/status/1800518368895934606?ref_src=twsrc%5Etfw">June 11, 2024</a></blockquote><br>

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">a b test <a href="https://t.co/kBzxvGL91t">pic.twitter.com/kBzxvGL91t</a></p>&mdash; tldraw (@tldraw) <a href="https://twitter.com/tldraw/status/1800848829065068843?ref_src=twsrc%5Etfw">June 12, 2024</a></blockquote><br>

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">Bee maths <a href="https://t.co/NPzfWl6UrS">pic.twitter.com/NPzfWl6UrS</a></p>&mdash; tldraw (@tldraw) <a href="https://twitter.com/tldraw/status/1801996964940095585?ref_src=twsrc%5Etfw">June 15, 2024</a></blockquote><br>

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">maths is solved <a href="https://t.co/kgbc1soUhr">https://t.co/kgbc1soUhr</a> <a href="https://t.co/g9QwcICglB">pic.twitter.com/g9QwcICglB</a></p>&mdash; tldraw (@tldraw) <a href="https://twitter.com/tldraw/status/1801217844576747995?ref_src=twsrc%5Etfw">June 13, 2024</a></blockquote>

### [Vision] [Gemini spatial example](https://gemini-spatial-example.grantcuster.com/)

Image analysis and labelling using gemini flash.
![Gemini spatial example](https://github.com/GrantCuster/gemini-spatial-example/raw/main/gemini-spatial-example.gif)
See also:

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">Alright Gemini&#39;s vision capabilities are really good. All I sent to Gemini was the photo and some instructions — the SVG on top was 100% generated by Gemini, including the coordinates etc. <a href="https://t.co/wwv4a6maEa">pic.twitter.com/wwv4a6maEa</a></p>&mdash; Blixt (@blixt) <a href="https://twitter.com/blixt/status/1799007168815141163?ref_src=twsrc%5Etfw">June 7, 2024</a></blockquote>

### [Vision] Recognizing actions on computer

Gemini detects which application is used and which action is used in the app.

<blockquote class="twitter-tweet" data-media-max-width="560"><p lang="en" dir="ltr">I am building a system to teach Gemini Flash new skills by observing the actions I take on my computer so it can repeat them.<br><br>I found a way to achieve 100% accuracy in Gemini&#39;s ability to recognize what I am clicking.<br><br>The trick? <br>Draw a blue circle where the click happens. 🔵 <a href="https://t.co/sxj6BcXSta">pic.twitter.com/sxj6BcXSta</a></p>&mdash; Pietro Schirano (@skirano) <a href="https://twitter.com/skirano/status/1798789123391762935?ref_src=twsrc%5Etfw">June 6, 2024</a></blockquote>

### [Vision] Drawings labelling in [<tldraw/>](https://tldraw.dev/)

A Gemini API integration that labels your drawings.
![tldraw](https://pbs.twimg.com/tweet_video_thumb/GPOT8XtXAAEHyxh.jpg)

<blockquote class="twitter-tweet" data-media-max-width="560"><p lang="en" dir="ltr">this demo may seem un-flashy but its actually huge for letting models interact better with a canvas, and also potentially massive for accessibility use cases <a href="https://t.co/58MFuLQ3kP">https://t.co/58MFuLQ3kP</a></p>&mdash; Lu wilson 🏳️‍🌈🏳️‍🌈 (@TodePond) <a href="https://twitter.com/TodePond/status/1797949557042753947?ref_src=twsrc%5Etfw">June 4, 2024</a></blockquote>

### [Vision and Code generation] [Gemini UI to Code Streamlit App](https://github.com/Doriandarko/gemini-ui-to-code)

Generates an HTML page from an image.

![Gemini UI to Code Streamlit App](https://pbs.twimg.com/ext_tw_video_thumb/1797737995325362176/pu/img/sA48r-MQRQouOJnW.jpg)
<blockquote class="twitter-tweet" data-media-max-width="560"><p lang="en" dir="ltr">Introducing Gemini UI to Code 🧑‍💻<br><br>A small but powerful app that uses an agentic framework to convert an image to code.<br><br>Perfect as a starter template or for learning new tricks.<br><br>Thanks to its improved Vision capabilities, Gemini 1.5 Pro is perfect for this task. 🪄 <a href="https://t.co/QfNi0q4ygL">pic.twitter.com/QfNi0q4ygL</a></p>&mdash; Pietro Schirano (@skirano) <a href="https://twitter.com/skirano/status/1797738751113998345?ref_src=twsrc%5Etfw">June 3, 2024</a></blockquote>

### [Vision] [Gemini helping to play super mario 64](https://t.co/doTngufjFL)

Gemini recognize the game, and the4 levels and provide advices when asked.

![Gemini helping to play super mario 64](https://pbs.twimg.com/ext_tw_video_thumb/1792945797765431296/pu/img/o4b_hjENB5fRhtSQ.jpg)

<blockquote class="twitter-tweet" data-media-max-width="560"><p lang="en" dir="ltr">I built my own omni assistant using Gemini 1.5 Flash to guide me through Super Mario 64. <br><br>Gemini can see what I do on my screen and communicate with me in real time via voice, and thanks to the long 1M context, it has a memory of everything we do together. <br><br>Incredible. <a href="https://t.co/doTngufjFL">pic.twitter.com/doTngufjFL</a></p>&mdash; Pietro Schirano (@skirano) <a href="https://twitter.com/skirano/status/1792948429754151293?ref_src=twsrc%5Etfw">May 21, 2024</a></blockquote>