Repository files navigation

Lunary helps developers of LLM Chatbots develop and improve them.

• 🖲️ Conversation & feedback tracking
• 💵 Analytics (costs, token, latency, ..)
• 🔍 Debugging (logs, traces, user tracking, ..)
• ⛩️ Prompt Directory (versioning, team collaboration, ..)
• 🏷️ Datasets (for evaluation, fine-tuning, ..)
• 🧪 Topic & sentiment analysis

It also designed to be:

• 📝 Easy to use
• 📦 Fast to integrate (2 minutes)
• 🧑‍💻 Self-hostable

Modules available for:

• JavaScript
• Python

Lunary natively supports:

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

Additionally you can use it with any other LLM by manually sending events.

Full documentation is availableon the website.

We offera hosted version with a generous free tier.

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

1. Clone the repository
2. Setup a PostgreSQL instance (version 15 minimum)
3. Copy the content ofpackages/backend/.env.example topackages/backend/.env and fill the missing values
4. Copy the content ofpackages/frontend/.env.example topackages/frontend/.env and fill the missing values
5. Runbun install
6. Runbun run migrate:db
7. Runbun run dev

You can now open the dashboard athttp://localhost:8080.When using our JS or Python SDK, you need to set the environment variableLUNARY_API_URL tohttp://localhost:3333. You can useLUNARY_VERBOSE=True to see all the event sent by the SDK

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

This project is licensed under the Apache 2.0 License.