Arc Storage Backend
Memtrace requires an Arc instance as its storage backend. All memories are stored in Arc's time-series format, providing high-performance temporal queries and efficient compression.
Claude Integration
Complete examples showing how to use Memtrace with the Anthropic Claude API for agent memory.
OpenAI Integration
Complete guide for using Memtrace with both the OpenAI API and OpenAI Agents SDK for agent memory.
MCP Server
Memtrace ships an MCP (Model Context Protocol) server that exposes memory tools over stdio. This enables integration with any MCP-compatible client — Claude Code, Claude Desktop, Cursor, Windsurf, Cline, Zed, VS Code Copilot, Gemini CLI, and more.