Demo • Use cases • Features • Tutorials • SDKs • Contributions
Gagarin is a service for creating and managing chatbots and agents. You can choose your LLM providers and your prompts. Your agents can interact with the world around them through tools. Using retrieval augmented generation (RAG) they can learn about various topics, including your privately hosted data.
@TODO
Gagarin lets you add and manage different LLM providers in a uniform way. You can create agents, give them prompts, determine which tools and information they can access, and chat with them from any interface you want. You can use the model that is best for your use case without worrying about lock-in.
- Add LLM providers
- Create agents with specific prompts
- Give those agents access to specific tools
- Give those agents access to specific information
- Create as many agents or instances of those agents as you'd like
- Create and interact with agents programmatically through a simple API, or use an SDK
Authorization: Bearer <YOUR_JWT>
@TODO
If you are planning to create or interface with agents, you can do so via the API or one of the SDKs below:
- Python - coming soon!
- Typescript - coming soon!
- Javascript - coming soon!
Gagarin is an open-source project, and contributions are welcome. If you want to contribute, you can create new features, fix bugs, or improve the infrastructure. Please refer to the CONTRIBUTING.md file in the repository for more information on how to contribute.
To see how to contribute, visit Contribution guidelines