Right now, it’s a bit like Vercel AI + LangChain + Pinecone in one Javascript SDK.

The repo is https://github.com/polyfire-ai/polyfire-js, our home page is https://polyfire.com.

Last June we were working on AI-generated docs but we didn’t quite understand how to make it work. So in July, we decided to open-source everything and focus on the underlying infrastructure.

Before this startup, I built at least 20 different apps with Firebase. So I thought it could be really cool to build something like Firebase but to make AI apps.

Therefore, Polyfire’s goal is to be simple. Setup takes a couple of lines of code, and then you can call text and image models from your Javascript frontend. It also includes a vector store so you can easily add semantic context to your calls with embeddings.

We have more things in the SDK Library like a Chat abstraction with automatic long term memory, DataLoader (e.g. to load text or audio files) and a system to turn prompt in environment variables. We tried to detail as much as possible in our docs: https://docs.polyfire.com.

We want to add many more things, your feature requests are welcomed!

Our goal right now is to make the best tool to build projects during hackathons: making it super easy to build and experiment with LLMs by adding more integrations, models, and features so hackers have many options. We think we can make something great if we can integrate in one experience the top 10-15 tools people need building AI apps.

Give it a look: https://github.com/polyfire-ai/polyfire-js. Let us know what you think!