Caution

Attention: llm.report is no longer actively maintained. This project was unable to find a sustainable business model, and the founders have moved on to other projects. If you are interested in maintaining or further developing this project, message me on twitter

llm.report

An open-source logging and analytics platform for OpenAI

Introduction · Self Hosted Installation · Cloud Installation · Tech Stack · Contributing

Introduction

llm.report is an open-source logging and analytics platform for OpenAI: Log your ChatGPT API requests, analyze costs, and improve your prompts.

Here are some of the features that llm.report provides out-of-the-box:

• OpenAI API Analytics
• Logs
• User Analytics

OpenAI API Analytics

No-code solution to analyze your OpenAI API costs and token usage.

Logs

Log your OpenAI API requests / responses and analyze them to improve your prompts.

User Analytics

Calculate the cost per user for your AI app.

Self-Hosted Installation

1. Clone the repo

git clone https://github.com/dillionverma/llm.report.git

2. cd into the repo

cd llm.report

3. Install dependencies

yarn

4. Setup environment variables

cp .env.example .env

• Generate NEXTAUTH_SECRET using openssl rand -base64 32 and add it to .env

5. Quickstart

• Requires Docker and Docker Compose to be installed.
• Will start a local Postgres instance with a few test users - the credentials will be logged in the console

yarn dx

Open http://localhost:3000 with your browser!

Tech Stack

• Next.js – framework
• Typescript – language
• Tailwind – CSS
• Shadcn – App UI components
• Magic UI – Marketing UI components
• Postgres – database
• NextAuth.js – auth
• Stripe – payments
• Resend - emails

Contributing

Here's how you can contribute:

• Open an issue if you believe you've encountered a bug.
• Make a pull request to add new features/make quality-of-life improvements/fix bugs.

Star History

License

Inspired by Dub and Plausible, both are open-source under the GNU Affero General Public License Version 3 (AGPLv3) or any later version. You can find it here. The reason for this is that we believe in the open-source ethos and want to contribute back to the community.

Credits

• OpenAI – for creating ChatGPT
• shadcn-ui – for making it easy to build beautiful UIs
• tremor.so – beautiful dashboard componenets
• mintlify – beautiful documentation
• screen.studio – the best video recording tool
• vercel – for making next.js and making it easy to build powerful apps
• Dub – for inspiring me to open-source this project