MemoryRouter

Integrations

Every AI you use.
One memory.

Your AI forgets what you told it yesterday. MemoryRouter keeps your conversational memory in one place, so you can bring your context into chat assistants, coding agents, and the apps you build. Choose your tool to get connected.

Save my memories

01 / 03 entries

Chat assistants

Your context, wherever the conversation happens.

02 / 13 entries

Coding agents

Keep the decisions. Pick up the project.

  • Claude Code

    Native hooks

    Recall project context and capture conversations across sessions and compaction.

    npx -y memoryrouter-claude init
  • Codex

    Native hooks + OAuth

    Give Codex persistent project memory with automatic recall and turn capture.

    pbpaste | npx -y memoryrouter-codex init --scope user --auth oauth --api-key-stdin
  • OpenClaw

    Native plugin

    Carry conversational memory across agent sessions, channels, and model switches.

    openclaw plugins install npm:mr-memory
  • DeepSeek Harness

    Native plugin

    Share memory across dsh’s Web UI, messaging gateways, and headless sessions.

    dsh plugin --profile <your-profile> add dsh-memoryrouter
  • Hermes Agent

    Native plugin

    Automatically capture clean conversations and recall relevant context across Hermes sessions.

    pip install hermes-memoryrouter hermes-memoryrouter install hermes config set memory.provider memoryrouter
  • NemoClaw

    Sandbox setup

    Connect a sandboxed NemoClaw agent to your MemoryRouter vault.

    npx @memoryrouter/nemoclaw setup --sandbox my-assistant --api-key <your-memory-key>
  • Cursor

    Custom base URL

    Bring your memory into Cursor through its custom OpenAI-compatible connection.

    https://api.memoryrouter.ai/v1
  • Windsurf

    Custom base URL

    Use shared memory in Windsurf configurations that expose a custom provider base URL.

    https://api.memoryrouter.ai/v1
  • Cline

    Custom base URL

    Connect Cline using its OpenAI-compatible provider and a custom base URL.

    https://api.memoryrouter.ai/v1
  • Continue

    Custom base URL

    Add persistent context to existing Continue installations using an OpenAI-compatible provider.

    https://api.memoryrouter.ai/v1
  • Aider

    Custom base URL

    Carry project context into Aider through the MemoryRouter proxy.

    https://api.memoryrouter.ai/v1
  • Cody

    Custom base URL

    Let a Cody Enterprise administrator configure a compatible model connection to the proxy.

    https://api.memoryrouter.ai/v1
  • Zed

    Custom base URL

    Connect Zed’s native assistant through a custom OpenAI- or Anthropic-compatible provider.

    https://api.memoryrouter.ai/v1

03 / 08 entries

Frameworks and protocols

Build memory into the tools you make and the stack you already use.

04 / 04 entries

Data and imports

Bring the history. Keep the continuity.

One account. Your memory.

Change tools.
Not your starting point.

Connect the same vault in each tool. Chat connectors search and save when asked; hooks and API integrations handle memory through their own workflows.

Planning a setup? Browse the integration docs, compare the coding-tool connection options, or follow the OpenClaw multi-agent guide. For existing files and conversations, start with the import overview.