Agent Switchboard

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

Cursor and other MCP clients
{
  "mcpServers": {
    "memorylake": {
      "url": "https://app.memorylake.ai/memorylake/mcp/v2"
    }
  }
}
Claude Code
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

Base URL
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.

Memory & Stateremote-mcplong-term-memorymultimodal-memorydocument-searchrest-apiopenclaw-plugin
Visit Agent
memorylake
Multimodal memory platform for agents: store and search memories and documents across projects through a REST API or a hosted OAuth MCP server.
try this first
Ask your assistant, with MemoryLake connected:
Use MemoryLake to run hybrid keyword and semantic search: ‹what you need›search-memory
Use MemoryLake to search memories: ‹what you're looking for›add-forget-memories
Use MemoryLake to run sandboxed Python: ‹what you need›analyze-files
use it now
{"mcpServers":{"memorylake":{"url":"https://app.memorylake.ai/memorylake/mcp/v2"}}}mcp.config
claude mcp add --transport http memorylake https://app.memorylake.ai/memorylake/mcp/v2mcp.claude-code
OAuth 2.0: you sign in with MemoryLakeapi.auth
fields
nameMemoryLake
providerMemoryLake
urlhttps://docs.memorylake.ai/features/memorylake/mcp-servers/overview
categoriesmemory-state
accessmcp · api
authoauth2
streamingfalse
pushfalse
verifiedtrue
officialfalse
sponsoredfalse
tagsremote-mcp, long-term-memory, multimodal-memory, document-search, rest-api, openclaw-plugin
skills
search-memorySearch MemoriesRun hybrid keyword and semantic search across a project…
add-forget-memoriesAdd and Forget MemoriesAdd, search, trace and forget memories and resolve conf…
analyze-filesAnalyze Project FilesRun sandboxed Python with pandas and numpy over project…
query-databasesQuery Connected DatabasesAsk natural-language questions that run as SQL against …
alternatives
/agents/memorylake/alternatives8 listedconfigure, tencentdb-agent-memory, ai-memory
compare
/compare?a=memorylake&b=configure&c=tencentdb-agent-memorywith configure, tencentdb-agent-memory