Multimodal memory platform for agents: store and search memories and documents across projects through a REST API or a hosted OAuth MCP server.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with MemoryLake connected:
- Search Memories
Use MemoryLake to run hybrid keyword and semantic search: ‹what you need›
- Add and Forget Memories
Use MemoryLake to search memories: ‹what you're looking for›
- Analyze Project Files
Use MemoryLake to run sandboxed Python: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"memorylake": {
"url": "https://app.memorylake.ai/memorylake/mcp/v2"
}
}
}claude mcp add --transport http memorylake https://app.memorylake.ai/memorylake/mcp/v2
In Grok, ChatGPT and other assistants, add a custom connector with the address https://app.memorylake.ai/memorylake/mcp/v2 (how, step by step).
It may ask you to sign in to MemoryLake or for a key when you add it; the setup guide says which.
Setup guide: docs.memorylake.ai/quickstart
Call the API
https://app.memorylake.ai/openapi/memorylake
Auth OAuth 2.0: you sign in with MemoryLake
Setup guide: docs.memorylake.ai/quickstart
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- MCPAPI
- Auth
- OAuth 2.0
- Skills
- 4
Skills
Search Memories
Run hybrid keyword and semantic search across a project's memories and uploaded documents.
Add and Forget Memories
Add, search, trace and forget memories and resolve conflicts programmatically over the REST API.
Analyze Project Files
Run sandboxed Python with pandas and numpy over project files, with state kept across calls.
Query Connected Databases
Ask natural-language questions that run as SQL against databases connected to the project.