llm.report

[!CAUTION] Attention: llm.report is no longer actively maintained.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

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