Files and knowledge
Supermemory for AI agents.
Make the right document easier to review.
Read accessible documents and related records in Supermemory. Prepare a source-grounded source-backed memory briefing within the selected account.
About Supermemory
With the Supermemory connector, your agent reads memory with the project’s Agent200 API key, so no separate Supermemory account or key is needed. It can search and list documents, read a document, and search memories, using only the tools your project allows.
Supermemory is a memory service that stores and retrieves context for AI applications.
Tools
What your agent can do in Supermemory.
Each tool is a capability the model can call. You decide which ones a project allows, and your Agent200 API key reaches them.
-
Search documents
Readsupermemory_search_documentsSearch indexed documents within a specified container.
-
Read a document
Readsupermemory_get_documentRetrieve one identified document when available.
-
List documents
Readsupermemory_list_documentsFind indexed documents in the key’s scope.
-
Search memories
Readsupermemory_search_memoriesSearch generated memories with source references.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Supermemory, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent search and read documents, and switch off
supermemory_search_memoriesif it should only work with documents. -
Restrict what the agent reaches
Choose the endpoints a project may use, for example documents but not memories. A call outside them is refused.
Get started
Connect Supermemory
in two steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Run with the Supermemory tools
Name the model and the tools. The model decides which Supermemory tools to call, and Agent200 executes them with your Agent200 API key.
run.jsConceptual exampleRun a request with the connector's tools 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);
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Supermemory connector and how to use it.
Connector: Supermemory, through Agent200. In code: "supermemory". What it does: Read accessible documents and related records in Supermemory. Prepare a source-grounded source-backed memory briefing within the selected account. Page: https://www.agent200.com/connectors/supermemory/ 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. Agent200 reaches Supermemory with the project's Agent200 API key. No separate Supermemory key is needed. 3. Read tools: supermemory_search_documents, supermemory_get_document, supermemory_list_documents, supermemory_search_memories. Name "supermemory" in the tools of a request; the model decides which tool to call. 4. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 5. Before a write, confirm with the user, unless they asked for that exact change. 6. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/supermemory/framework/claude/ https://www.agent200.com/connectors/supermemory/framework/chatgpt/ https://www.agent200.com/connectors/supermemory/framework/claude-code/ https://www.agent200.com/connectors/supermemory/framework/muse/ https://www.agent200.com/connectors/supermemory/framework/grok-bot/ https://www.agent200.com/connectors/supermemory/framework/openai-dots/ https://www.agent200.com/connectors/supermemory/framework/claude-duet/ https://www.agent200.com/connectors/supermemory/framework/hermes-agent/ https://www.agent200.com/connectors/supermemory/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/supermemory.md
Guides
Use Supermemory with the AI you build on.
Step-by-step setup for Supermemory with a specific model, assistant or agent framework.
-
Supermemory + Claude
How to connect Supermemory to Claude
-
Supermemory + ChatGPT
How to connect Supermemory to ChatGPT
-
Supermemory + Claude Code
How to connect Supermemory to Claude Code
-
Supermemory + Muse
How to connect Supermemory to Muse
-
Supermemory + Grok Bot
How to connect Supermemory to Grok Bot
-
Supermemory + OpenAI Dots
How to connect Supermemory to OpenAI Dots
-
Supermemory + Claude Duet
How to connect Supermemory to Claude Duet
-
Supermemory + Hermes Agent
How to connect Supermemory to Hermes Agent
-
Supermemory + OpenClaw
How to connect Supermemory to OpenClaw
FAQ
Supermemory and Agent200, answered.
What access does Supermemory need?
Use the Supermemory API key in secure configuration. The recorded key route has no user-info endpoint; use explicit container tags and application identity. Provider documentation.
Does a list include every record?
A semantic match is not proof of complete recall. Name returned sources and container scope, and allow for indexing or processing lag.
Can this workflow make changes?
The listed Supermemory operations are read-only. A proposed change in the agent answer does not edit the source.
How should I verify the answer?
Identify the selected document and compare the answer with document content, source and container tags. Disclose missing or inaccessible fields.
Are these exact runtime tool schemas?
The listed identifiers describe catalogue capabilities. Discover the actual runtime tool names and input schemas before executing a request.