# Build a Supermemory reader with ChatGPT Prepare a grounded source-backed memory briefing

> Use ChatGPT to build a separate read-only Supermemory assistant with Agent200. Ground the source-backed memory briefing in returned source data.

- Page: https://www.agent200.com/connectors/supermemory/framework/chatgpt/
- Connector: [Supermemory](https://www.agent200.com/connectors/supermemory.md)
- Framework: ChatGPT
- Updated: 2026-11-17

## Instructions for AI agents

Goal: connect Supermemory to ChatGPT with Agent200.
Guide: https://www.agent200.com/connectors/supermemory/framework/chatgpt/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Make sure Supermemory is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "supermemory" in the tools. The model decides when a Supermemory tool is needed; Agent200 executes the call.
5. Check it works with this request: "Read the Supermemory document I identify and prepare a source-backed memory briefing. Name the source and use only document content, source and container tags. State access gaps; do not change records."
   What should come back:
   - The selected document is identified.
   - Only the returned document content, source and container tags are reported.
   - Access gaps and missing context are explicit; no source data is changed.
6. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## Overview

Build a separate source-backed memory briefing application with Agent200. Use the runtime’s real schemas and preserve the authenticated user. This is an architecture guide, not a native installation in ChatGPT.

Start with one identified document. Preserve returned document content, source and container tags; report missing data and keep the workflow read-only.

Provider reference: [Supermemory API](https://api.supermemory.ai/reference).

Use the provider credential described on the Supermemory parent page. Keep it in secure configuration and verify the selected tenant or account before reading.

- **Connector:** [Supermemory](https://www.agent200.com/connectors/supermemory/)
- **Works with:** ChatGPT · Your own agent code
- **Authentication:** Your Agent200 API key
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [4 tools](https://www.agent200.com/connectors/supermemory/framework/chatgpt/#tools)
- **Model in examples:** `openai/gpt-5.6-sol`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **Supermemory enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **A model for your agent.** The examples use openai/gpt-5.6-sol, through the same Agent200 API key.

## Connect Supermemory to ChatGPT

### Step 1: Create your Agent200 API key

Create a key on the [API keys page](https://agent200.com/platform/apikeys/) and store it securely.

File `.env`:

```bash
# Keep the key out of your code, prompts and chats.
export AGENT200_API_KEY="paste-your-key-here"
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Inspect the real tool definitions

Confirm the actual Supermemory read operations and input schemas in your runtime.

### Step 3: Configure Supermemory access

Use the provider-issued credential through the supported Agent200 connection route. Confirm the account scope and inspect the advertised tools before reading.

### Step 4: Build and test the read-only answer

Prepare the source-backed memory briefing only from returned source data. The code example illustrates a sequence, not an SDK installation contract.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Search my memory for what we decided about pricing",
    tools: ["supermemory"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Test your connection

Ask: "Read the Supermemory document I identify and prepare a source-backed memory briefing. Name the source and use only document content, source and container tags. State access gaps; do not change records."

What should come back:

- The selected document is identified.
- Only the returned document content, source and container tags are reported.
- Access gaps and missing context are explicit; no source data is changed.

Check the selected document ID, account scope, read permission and pagination. A semantic match is not proof of complete recall. Name returned sources and container scope, and allow for indexing or processing lag.

## Supermemory tools ChatGPT can call

- **Search documents** (`supermemory_search_documents`, read): Search indexed documents within a specified container.
- **Read a document** (`supermemory_get_document`, read): Retrieve one identified document when available.
- **List documents** (`supermemory_list_documents`, read): Find indexed documents in the key’s scope.
- **Search memories** (`supermemory_search_memories`, read): Search generated memories with source references.

## How it works

1. **Your app sends the request.** It calls Agent200 with the model, instructions, the input and the Supermemory tools.
2. **The model picks a tool.** The model decides whether a Supermemory tool is needed, and with which arguments.
3. **Agent200 runs the call.** It reaches Supermemory with your Agent200 API key, within the endpoints your project allows, and returns the result to the model.
4. **Your app gets the result.** Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

**Permissions at every level.** Your project settings decide which services and endpoints the agent may use.

## Troubleshooting

### The source cannot be read

Check the selected document ID, account scope, read permission and pagination. A semantic match is not proof of complete recall. Name returned sources and container scope, and allow for indexing or processing lag.

## FAQ

### How do I verify this result?

Compare the named document and returned document content, source and container tags with the source. Treat missing information as missing, not as a fact.

### Is this a native product integration?

This describes a separate application built with Agent200 and ChatGPT; it does not install a connector into the ChatGPT app.

## Use Supermemory with another framework

- [Supermemory + Claude](https://www.agent200.com/connectors/supermemory/framework/claude.md)
- [Supermemory + Claude Code](https://www.agent200.com/connectors/supermemory/framework/claude-code.md)
- [Supermemory + Muse](https://www.agent200.com/connectors/supermemory/framework/muse.md)
- [Supermemory + Grok Bot](https://www.agent200.com/connectors/supermemory/framework/grok-bot.md)
- [Supermemory + OpenAI Dots](https://www.agent200.com/connectors/supermemory/framework/openai-dots.md)
- [Supermemory + Claude Duet](https://www.agent200.com/connectors/supermemory/framework/claude-duet.md)
- [Supermemory + Hermes Agent](https://www.agent200.com/connectors/supermemory/framework/hermes-agent.md)
- [Supermemory + OpenClaw](https://www.agent200.com/connectors/supermemory/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
