Integrate into Your Own Custom GPT

Add long-term memory to your own Custom GPTs with MemoryPlugin

Written by asad

Last updated 2 months ago

Add long-term memory functionality to your own Custom GPTs with MemoryPlugin! We make this very easy to do by providing everything you need to integrate our memory system.

What are Custom GPTs?

Custom GPTs are a feature in ChatGPT that let you create customized versions of ChatGPT with:

• Custom instructions and personality
• Document knowledge bases
• External API integrations
• Specialized functionality

With MemoryPlugin, you can add long-term memory functionality to any Custom GPT!

Key Concepts

Before setting up the integration, understand these concepts:

APIs

APIs let computer systems communicate. In Custom GPTs, APIs let your GPT use external tools like MemoryPlugin.

Step-by-Step Setup

Step 1: Access GPT Builder

1. Open the edit window for your existing Custom GPT, or create a new one
2. Navigate to the Configure tab
3. Scroll down to find the Actions section

Step 2: Create New Action

Within the Configure tab, you will see an Actions section if you scroll down:

1. Click Create new action

2. Click Import from URL
3. Enter this URL:
   https://www.memoryplugin.com/openapi.json
   

Step 3: Configure Authentication

1. In the Authentication section, click the Settings icon
2. Select API key
3. Choose Bearer from the options
4. Get your Auth Token from the MemoryPlugin Dashboard

5. Enter your token in the authentication setup

Your Auth Token is like a password to your account. Keep it confidential and regenerate it if accidentally exposed.

Account email independence: Your MemoryPlugin sign‑in email does not need to match the email you use on ChatGPT, Claude, TypingMind, or any other tool. Access and permissions are tied to your MemoryPlugin account (and API key when applicable), not third‑party logins.

Step 4: Add Instructions

Back in the Configure tab, you have an Instructions section. You need to instruct your GPT how it should use MemoryPlugin:

Add the MemoryPlugin instructions after your existing custom instructions:

VERY IMPORTANT: ALWAYS fetch all memories at the start of each chat before responding (unless explicitly instructed otherwise), so you have context about me and can help me better. Use the `GetMemoriesAndBuckets` operation to do this.

The `memory` tool allows you to persist information across conversations. Add to memory any information you want to remember. The information will appear in the context in future conversations.

- Memories are stored in "buckets"
- If you do not supply a bucket id when loading memories, all memories are loaded
- if you do supply a bucket id, only those buckets memories are loaded
- by default memories are added to the "General" bucket
- new buckets cannot be named "General"
- If you supply the bucketId when creating a new memory, it will be added to that bucket instead
- Do not guess bucket IDs, they are random
- When using bucket IDs, please make sure they are correct and are sent in the correct parameter.
- When explicitly instructed to add a memory by the user, follow the users instructions strictly.

I can use \m or +m as a shortcut to create a new memory.

- before using any tool, review the tool use instructions thoroughly
- Double-check the function schemas to make sure you are using the correct expected format.
- Make sure your tool and/or function call matches the expected format and schema
- if a JSON schema is specified, adhere to it strictly.
- Verify all your tool calls with the usage instructions in the system prompt.

Step 5: Save and Test

1. Click Save to save your action configuration
2. Test your Custom GPT by starting a new conversation
3. The GPT should automatically load your memories at the start

Visual Guide

1. Configure Tab

   Navigate to the Configure tab in your Custom GPT editor

2. Actions Section

   Scroll down to find the Actions section

3. Import API

   Import the MemoryPlugin OpenAPI specification

4. Set Authentication

   Configure Bearer token authentication with your API key

5. Add Instructions

   Include the MemoryPlugin prompt in your instructions

6. Test Integration

   Start a conversation to verify memory loading works

Features Your GPT Will Gain

Once integrated, your Custom GPT will be able to:

• Auto-load memories at the start of conversations
• Remember important information from previous chats
• Organize memories into different buckets/contexts
• Search through memories to find relevant information
• Persist knowledge across all conversations
• Share memories with other MemoryPlugin integrations

Best Practices

Memory Management

Instruct your GPT on what types of information to remember based on your use case

Bucket Strategy

Use specific buckets for different contexts or topics your GPT handles

User Shortcuts

Tell users about the \m and +m shortcuts for quick memory creation

Privacy

Be mindful of what information gets stored and inform users appropriately

Troubleshooting

OpenAPI import failed

Ensure you’re using the correct URL: https://www.memoryplugin.com/openapi.json

Authentication errors

Verify your Auth Token is correct and hasn’t expired. Regenerate if necessary.

Memories not loading

Check that the GPT instructions include the memory loading commands and are properly formatted.

Function call errors

Ensure the instructions emphasize following the schema and format requirements strictly.

Example Use Cases

• Personal Assistant GPT: Remember preferences, schedule, and important personal information
• Learning Companion: Track learning progress, remember concepts studied, and build knowledge
• Project Manager: Remember project details, team information, and progress across conversations
• Writing Assistant: Remember writing style, character details, plot points across sessions
• Customer Service: Remember customer interactions, preferences, and history

Next Steps

API Reference

Explore the full MemoryPlugin API capabilities

Memory Buckets Guide

Learn how to organize memories effectively