Build an AI Email Agent with Pipes — ⌘ Langbase

An AI powered email agent to help you analyze sentiment, summarize content, decides whether a response is needed or not, and generates replies for your emails. This agent is built by using multiple AI Pipes on Langbase which work with 30+ LLMs (OpenAI, Gemini, Mistral, Llama, Gemma, etc), any Data (10M+ context with Memory sets), and any Framework (standard web API you can use with any software).

Check out the live demo here.

Features

• 📧 AI Email Agent — Built with multiple AI Pipes on ⌘ Langbase
  • Email Sentiment – A pipe to analyze the sentiment of the incoming email
  • Summarizer – Summarizes the content of the email and make it less wordy for you
  • Email Decision Maker – A pipe that decides whether the email needs a response or not, and also the category and priority of the response
  • Pick Email Writer – A pipe that picks the tone for writing an email
  • Email Writer – A pipe that writes a response email as a reply to your email
• ⚡️ Streaming — Real-time experience with streamed responses
• 🔋 Responsive and open source — Works on all devices and platforms

Learn more

1. Check the AI Email Agent Pipes on ⌘ Langbase
2. Read the source code on GitHub for this example
3. Go through Documentaion: Pipe Quick Start
4. Learn more about Pipes & Memory features on ⌘ Langbase

Get started

Let's get started with the project:

To get started with Langbase, you'll need to create a free personal account on Langbase.com and verify your email address. Done? Cool, cool!

1. Fork the following pipes on ⌘ Langbase.
   1. Email Sentiment
   2. Summarizer
   3. Email Decision Maker
   4. Pick Email Writer
   5. Email Writer
2. Go to the API tab of each pipe to copy the pipe's API key (to be used on server-side only).
3. Download the example project folder from here or clone the repository.
4. cd into the project directory and open it in your code editor.
5. Duplicate the .env.example file in this project and rename it to .env.local.
6. Add the following environment variables:

sh
DownloadCopy code
1# Fork https://langbase.com/examples/email-sentiment pipe to get the API key
2# Replace `PIPE_API_KEY` with the copied API key of Code Alchemist Pipe.
3LANGBASE_AI_PIPE_SENTIMENT_API_KEY="PIPE_API_KEY"
4
5# Fork https://langbase.com/examples/summarizer pipe to get the API key
6# Replace `PIPE_API_KEY` with the copied API key of Code Alchemist Pipe.
7LANGBASE_AI_PIPE_SUMMARIZER_API_KEY="PIPE_API_KEY"
8
9# Fork https://langbase.com/examples/decision-maker pipe to get the API key
10# Replace `PIPE_API_KEY` with the copied API key of Code Alchemist Pipe.
11LANGBASE_AI_PIPE_DECISION_MAKER_API_KEY="PIPE_API_KEY"
12
13# Fork https://langbase.com/examples/pick-email-writer pipe to get the API key
14# Replace `PIPE_API_KEY` with the copied API key of Code Alchemist Pipe.
15LANGBASE_AI_PIPE_PICK_EMAIL_WRITER_API_KEY="PIPE_API_KEY"
16
17# Fork https://langbase.com/examples/email-writer pipe to get the API key
18# Replace `PIPE_API_KEY` with the copied API key of Code Alchemist Pipe.
19LANGBASE_AI_PIPE_EMAIL_WRITER_API_KEY="PIPE_API_KEY"

7. Now execute the following commands in your terminal to run the project:

sh
DownloadCopy code
1# Install the dependencies using the following command:
2pnpm install
3
4# OR if you are using npm, run the following command:
5npm install
6
7# Run the project using the following command:
8npm run dev

Your app template should now be running on localhost:3000

NOTE: This is a Next.js project, so you can build and deploy it to any platform of your choice, like Vercel, Netlify, Cloudflare, etc.

---

Authors

This project is created by Langbase team members, with contributions from:

• Ashar Irfan (@MrAsharIrfan) - Founding Engineer, Langbase

Built by ⌘ Langbase.com — Ship composable AI agents with hyper-personalized memory (RAG)!