> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memorylake.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Integrations Overview

> Bring MemoryLake memory into your agents and apps — OpenClaw plugins, REST API, and the MCP server

## Overview

Memory is only useful where you work. MemoryLake offers several integration paths, all reading and writing the same memory pool:

| Integration                               | Status         | Best for                                                                      |
| ----------------------------------------- | -------------- | ----------------------------------------------------------------------------- |
| **OpenClaw plugin**                       | ✅ Available    | Coding agents with automatic recall, capture, and file upload                 |
| **QClaw plugin**                          | ✅ Available    | Same plugin, QClaw runtime (`~/.qclaw/openclaw.json`)                         |
| **Hermes Agent**                          | ✅ Available    | One-line install of a memory-connected agent (macOS)                          |
| **REST API**                              | ✅ Available    | Full programmatic control from any language                                   |
| **MCP server (OAuth2)**                   | ✅ Available    | Claude Code, Codex, Cursor, Claude Desktop, and any OAuth2-capable MCP client |
| **Chrome extension, chat-history import** | 🔜 Coming soon | Guided setup per client                                                       |

Open **Integrations** in the [console](https://app.memorylake.ai) sidebar to see what's enabled for your account — each available card generates setup commands pre-filled with your project id and API key.

## OpenClaw / QClaw Plugin

The richest integration: install once and your agent gains **Auto-Recall** (retrieves relevant memories and document context before answering), **Auto-Capture** (durable facts from each conversation are stored and merged in the background), and **Auto-Upload** (files you share in chat land in your project automatically) — plus explicit memory tools and a CLI.

<CardGroup cols={2}>
  <Card title="Plugin Reference" icon="puzzle-piece" href="/features/memorylake/mcp-servers/openclaw-plugin">
    Configuration, tools, CLI, skills, and per-agent scoping.
  </Card>

  <Card title="Coding Agents Scenario" icon="terminal" href="/scenarios/coding-agents">
    The end-to-end walkthrough with day-to-day examples.
  </Card>
</CardGroup>

## REST API

Everything the console does, programmatically: projects, document upload/search, memory add/search/trace/forget, and conflict resolution.

* **Base URL**: `https://app.memorylake.ai/openapi/memorylake`
* **Auth**: `Authorization: Bearer sk-…` ([create a key](/authentication))
* **Live spec**: `https://app.memorylake.ai/openapi/memorylake/api-docs/open-api`

The console's **Integrations → API** card also generates an AI-ready prompt describing the endpoints, so you can hand your agent the API surface directly. Full documentation in the [API Reference](/features/memorylake/api-reference/overview).

## MCP Server

MemoryLake runs a **remote MCP server** (Model Context Protocol over HTTP, authorized with standard OAuth2) at:

```text theme={null}
https://app.memorylake.ai/memorylake/mcp/v2
```

Connect Claude Code with one command — `claude mcp add --transport http --scope user memorylake <url>` — or point Codex, Cursor, or Claude Desktop at the same URL. You pick the workspace and boundary on the OAuth consent screen, so no secret ever lands in a config file. See [Connect via MCP](/features/memorylake/mcp-servers/creating-api-keys) for per-client setup.

Connected clients get search and analysis tools over the memories and documents in scope:

| Tool                                            | What it does                                                                                        |
| ----------------------------------------------- | --------------------------------------------------------------------------------------------------- |
| `search_memory`                                 | Hybrid keyword + semantic search across the project's memories and documents                        |
| `fetch_memory`                                  | Fetch detailed metadata and download links for specific results                                     |
| `get_memorylake_metadata`                       | Project overview — file counts by type, spreadsheet sheet names, document stats                     |
| `create_memory_code_runner` / `run_memory_code` | Sandboxed Python (pandas, numpy, …) for analyzing project files, with state persisting across calls |
| `nl_query_database`                             | Natural-language SQL over connected databases (where configured)                                    |

OpenAI-protocol clients (like ChatGPT) are automatically served simplified `search` / `fetch` variants of the same tools — one endpoint adapts to the client.

## Which Integration Should I Use?

* **You use an MCP-capable client** (Claude Code, Codex, Cursor, Claude Desktop) → MCP. One command, OAuth2, nothing to store.
* **You want automatic memory in a coding agent** → OpenClaw/QClaw plugin. Auto-recall, auto-capture, and auto-upload beat manual tool calls.
* **You're building a product** → REST API (generally available) or [Memory Router](/features/memory-router/overview) (private preview) for call-level memory.
* **You want MemoryLake's models too** → add the [Model Router](/features/model-router/overview) — same key, OpenAI-compatible endpoint, plus the `memorylake-models-openclaw` plugin for OpenClaw.

## Next Steps

<CardGroup cols={2}>
  <Card title="OpenClaw Plugin Reference" icon="puzzle-piece" href="/features/memorylake/mcp-servers/openclaw-plugin">
    Install, configure, and master the agent plugin
  </Card>

  <Card title="Connect via MCP" icon="plug" href="/features/memorylake/mcp-servers/creating-api-keys">
    Per-client setup for Claude Code, Codex, Cursor, and Desktop
  </Card>
</CardGroup>