Claw Recall Memory Server

Example Use Cases

• 1

  Recover lost conversation context after compaction or restarts.

• 2

  Search across multiple data sources including conversations, emails, files, and Slack.

• 3

  Capture and share insights or monitor memory usage via MCP tools.

Description

Claw Recall provides a self-hosted memory system for AI agents by indexing conversations, emails, files, and Slack messages into a searchable SQLite database with full-text and semantic search capabilities. It supports multiple data sources and exposes 8 MCP tools for agents to search, browse, capture, and monitor memory. The server can be accessed locally via stdio, remotely via SSE HTTP, or through a REST API, enabling agents to recover lost context and share insights seamlessly. It includes noise filtering, secret redaction, incremental indexing, and embedding caching for efficient and secure operation.