Skip to main content
Helicone OSS LLM Observability

Manual Self-Hosting

Deploy your own instance of Helicone. Follow our step-by-step guide to set up a local, self-hosted version of the LLM observability platform.
1 min read
Warning

Deploy with Docker Compose! We recommend deploying with Docker Compose, as it works easily with just one line.

Note we moved the old manual setup with Supabase here

At Helicone we believe that open-source software makes the world a better place. We are committed to open-source and we made a guide to make it easy for you to deploy your own instance of Helicone.

Running locally#

Running Helicone locally should be super easy. Just a few scripts.

Please clone our Repo and follow the instructions below.

Step 1 - Install all the things#

Requirements

  • Docker

Install Yarn#

Step 2 - Start all the services#

Start Databases#

Start mailhog server (local email testing)#

Start Jawn (Backend + Main Proxy)#

In a new terminal tab, run the following:

Start Web#

In a new terminal tab, run the following:

Step 3 - Setup your instance#

You are done!

Note

Jawn no longer proxies LLM traffic: the /v1/gateway/* routes have been removed. To proxy requests through a self-hosted deployment, run the AI Gateway alongside Jawn.

You can login to Helicone at http://localhost:3000 with the following credentials:

User: test@helicone.ai Password: password

Change the Org to Organization for Test and then you should be able to see your requests!

Please do not hesitate to reach out on discord if you have any questions.