Open-Source Platform for Custom AI Agents

Docs  ·   Slack  ·   X

🌈 Why Latitude?

Latitude is an open-source platform for both AI agents and prompt engineering. It covers the entire lifecycle: from design and testing to deployment, observability, and scaling.

Key features include:

• Collaborative Design → version prompts and agents with your team
• Playground → test interactively with different inputs, parameters, and configurations
• Evaluations → choose from built-in evals, use LLM-as-judge, or add human-in-the-loop
• AI Gateway → deploy as API endpoints that stay up-to-date with published changes
• Logs & Observability → monitor costs, latency, and performance in real time
• Experiments → run controlled tests across models and providers
• Datasets → manage test data for batch evaluations and regression testing
• Integrations → connect with 2,500+ tools

📚 Table Of Contents

• Getting Started
• Custom AI Agents
• Prompt Engineering
• Evaluations
• Datasets & Testing
• Integrations & Deployment
• Self-Hosting
• Advanced: PromptL
• Contributing
• License

⚡ Quick start

Latitude offers two deployment options:

1. Latitude Cloud: A fully managed solution that allows you to get started quickly without worrying about infrastructure.
2. Latitude Self-Hosted: An open-source version that you can deploy and manage on your own infrastructure for complete control and customization.

Choose the option that best fits your needs and follow the corresponding instructions below.

Latitude Cloud

To get started with Latitude, follow these steps:

1. Sign up for Latitude → Visit our website and create your account.

2. Create a new project → Once logged in, create a project to organize your agents, prompts, and evaluations.

3. Build your first agent or prompt →

   • Agent: use the Editor to configure a simple workflow or autonomous agent.
   • Prompt: start with a basic task, like generating a short story or answering a question.

4. Test in the playground → Run prompts or agents interactively with different inputs and observe responses.

5. Evaluate in batch → Upload a dataset and run evaluations to measure performance across scenarios.

6. Deploy → Publish your prompt or agent as an endpoint for easy integration with your applications.

7. Monitor and evaluate → Use Logs & Observability to review performance, costs, and latency over time.

8. Iterate and improve → Refine prompts or agents based on evaluation results, or create new versions.

9. Collaborate with your team → Invite team members to your Latitude workspace to collaborate on building, testing, and improving.

For more details on each step, see our documentation or join the community.

Latitude Self-Hosted

Follow the instructions in the self-hosted guide to get started with Latitude Self-Hosted.

After setting up Latitude Self-Hosted, you can follow the same steps as in the Latitude Cloud guide to create, test, evaluate, and deploy your prompts.

👥 Community

The Latitude community can be found on Slack

where you can ask questions, voice ideas, and share your projects with other people.

🤝 Contributing

Contributions to Latitude are welcome and highly appreciated. You can find an in-depth explanation of the repo and its architecture here

If you are interested in contributing, please join us on our Slack community, open an issue, or contribute a pull request.

📄 License

Latitude is licensed under the LGPL-3.0.

Alternatively, we offer a more permissive commercial license for those who need it. Please contact us at [email protected] for more information.

🔗 Links

• Home page
• Documentation
• Slack community
• X / Twitter

Made with ❤️ by the Latitude Team