barbudour / lunary

The production toolkit for LLMs. Observability, prompt management and evaluations.

📈 lunary

Open-source observability & prompt platform for LLMs

website - docs - self host

Features

Lunary helps AI devs take their apps in production, with features such as:

• 💵 Analytics (cost, token, latency, ..)
• 🔍 Monitoring (logs, traces, user tracking, ..)
• ⛩️ Prompt Templates (versioning, team collaboration, ..)
• 🏷️ Creat fine-tuning datasets
• 🖲️ Chat & feedback tracking
• 🧪 Evaluations

It also designed to be:

• 🤖 Usable with any model, not just OpenAI
• 📦 Easy to integrate (2 minutes)
• 🧑‍💻 Simple to self-host

Demo

demo720.mp4

⚙️ Integration

Modules available for:

• JavaScript
• Python

Lunary natively supports:

• LangChain (JS & Python)
• OpenAI module
• LiteLLM

Additionally you can use it with any framework by wrapping the relevant methods.

📚 Documentation

Full documentation is available on the website.

☁️ Hosted version

We offer a hosted version with a free plan of up to 1k requests / days.

With the hosted version:

• 👷 don't worry about devops or managing updates
• 🙋 get priority 1:1 support with our team
• 🇪🇺 your data is stored safely in Europe

Running locally

Lunary is powered by Node.js.

To run it locally, you'll need access to a Postgres database to set as the DATABASE_URL in your .env file.

# Clone the repository
git clone https://github.com/lunary-ai/lunary

# Copy env variables
cp .env.example .env

# Install dependencies
npm install

## Run DB migrations
npm run migrate:db

# Run the development server
npm run dev

🙋 Support

Need help or have questions? Chat with us on the website or email us: hello [at] lunary.ai. We're here to support you every step of the way.

License

This project is licensed under the Apache 2.0 License.