AI is everywhere these days. But instead of just learning about AI, why not build something with it?
There are many open-source AI tools on GitHub that you can use in your own projects. You can build chatbots, generate images, work with documents, run AI models, create AI agents, and more.
So, in this post, I’m sharing 20 GitHub repositories you can check out and use to build AI projects.
Most of them are free and open source, so you can try them out and learn as you build.
Let’s get started!
1. AnythingLLM
AnythingLLM lets you create your own AI assistant that can work with your documents.
You can add your files and then chat with them using an AI model.
It’s useful if you want to experiment with a private AI assistant using your own data.
2. AutoGen
AutoGen is a framework from Microsoft for building applications with multiple AI agents.
Different agents can communicate with each other and work together to solve a problem.
You can use it to experiment with multi-agent AI systems.
3. Chroma
Chroma is a vector database designed for AI applications.
It helps you store and search information called “embeddings”.
This becomes useful when you want an AI application to find relevant information from your own documents or data.
For example, you could use it to build a chatbot that answers questions about a collection of documents.
4. ComfyUI
ComfyUI is another tool for working with image generation models.
It uses a node-based interface, where you connect different steps together to create an image-generation workflow.
It takes some time to learn, but it gives you a lot of control over how your workflow works.
5. Crawl4AI
AI applications often need information from websites.
Crawl4AI is an open-source web crawler designed to extract web content in a format that works well with AI applications.
You can use it when building projects that need to collect and process information from websites.
6. CrewAI
CrewAI helps you build applications where multiple AI agents work together.
You can give each agent a different role.
For example, one agent researches a topic, another writes the content, and another reviews it.
The agents can then work together to complete a task.
7. Instructor
Instructor makes it easier to get structured responses from AI models.
For example, instead of asking an AI model for plain text, you can tell it that you want the answer in a specific format.
This can be useful when building applications that need reliable data from an AI model.
8. Gradio
Gradio helps you turn a machine learning model or Python function into a simple web interface.
You don’t need to know much frontend development to get started.
For example, you can quickly create a small app where users upload an image, and your AI model processes it.
9. LangChain
LangChain helps you build applications with large language models (LLMs).
You can use it to connect an AI model to your data, APIs, tools, and other services.
For example, you can use LangChain to build a chatbot that can search your documents and answer questions about them.
10. LlamaInde
LlamaIndex helps you connect AI models to your own data.
You can use it with documents, databases, APIs, and other sources.
It’s especially useful when you want to build a system where an AI model can search your data and answer questions about it.
11. LocalAI
LocalAI lets you run AI models on your own hardware and provides an API that is compatible with many OpenAI API use cases.
This can be useful if you want to experiment with local AI models instead of relying completely on cloud-based services.
12. Mem0
Mem0 helps AI applications remember information between conversations.
For example, an AI assistant could remember useful details from previous conversations instead of starting from scratch every time.
This can help you build more personalised AI applications.
13. Ollama
Ollama lets you run AI language models directly on your computer.
You can run models like Llama, Mistral, Gemma, and Phi directly on your computer, without sending your prompts to a cloud AI service.
It’s a great place to start if you want to experiment with local AI models.
14. Open WebUI
Open WebUI is a web interface for working with AI models.
You can connect it to local models through tools like Ollama and chat with them through a clean interface.
If you want to run AI models yourself but still want a ChatGPT-like experience, this is worth checking out.
15. Qdrant
Qdrant is another vector database that you can use for AI applications.
It helps you store and search embeddings quickly.
It’s useful for projects that need to find information based on meaning, rather than just matching exact words.
16. Stable Diffusion Web UI
Stable Diffusion Web UI, also known as AUTOMATIC1111, gives you an interface for generating images with Stable Diffusion.
Instead of working with the model directly, you can use a web interface to create images from text prompts.
You can also add extensions and experiment with different models.
17. Streamlit
Streamlit makes it easy to turn Python code into interactive web apps.
It’s commonly used for data science and machine learning projects.
You can use it to quickly build things like:
- AI chatbots
- Data dashboards
- Image tools
- RAG applications
- Machine learning demos
18. Transformers.js
Transformers.js from Hugging Face lets you run machine learning models using JavaScript.
You can run some models directly in the browser or with Node.js.
This means you can experiment with AI features without always needing a Python backend.
It’s a great option for JavaScript developers who want to explore AI.
19. Vercel AI SDK
If you’re a JavaScript or TypeScript developer, Vercel AI SDK can help you add AI features to your web apps.
It works with popular AI providers and makes it easier to build features such as:
- AI chat
- Streaming responses
- AI-powered interfaces
- Text generation
It’s especially useful if you’re building with React or Next.js.
20. Whisper
Whisper is an open-source speech recognition model from OpenAI.
It can turn spoken audio into text and supports many languages.
You can use it to build things like:
- Audio transcription tools
- Meeting note apps
- Voice note transcribers
- Podcast transcription tools
That’s all for today!
I hope you found a few repositories worth checking out. Whether you want to run AI models locally, build a chatbot, create AI agents, generate images, or work with your own data, there’s plenty here to explore.
You don’t need to try all 20. Pick one that looks interesting and start building. You’ll learn a lot by experimenting and making something of your own.
For paid collaboration, connect with me at: connect@shefali.dev
If you enjoy my work and want to support what I do buy me a coffee!
Every small gesture keeps me going! 💛
Follow me on X (Twitter) to get daily web development tips & insights.
Enjoyed reading? You may also find these articles helpful.
Python Libraries Every Developer Should Know
Explore 16 useful Python libraries every developer should know about, from APIs and automation to data science and web development.
shefali.dev
Python Roadmap: Learn Step by Step
A complete Python roadmap for beginners, covering basics to advanced concepts in a clear, step-by-step learning order.
shefali.dev
Top comments (0)