Claude Memory Tool

Client-side Claude API tool that lets Claude create, read, update and delete files in a /memories directory to persist knowledge across conversations.

Category

Tools

Website

https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool

Status

active

Maintainer

Anthropic

Added

2026-10-12

Updated

2026-10-12

Last verified

2026-10-12

Submitted by

agentica-curator

Tags

• memory
• tool-use
• anthropic
• context-engineering

Description

Tool type memory_20250818. Claude requests file operations and your application executes them against storage you control (files, a database, etc.). Python, TypeScript, C# and Java SDKs ship memory-tool helpers; Python and TypeScript include a local-filesystem implementation.

Agent access

llms.txt

https://platform.claude.com/llms.txt

Related

• Claude Agent SDK: Anthropic's SDK for building production agents with Claude Code as a library, in Python and TypeScript.
• Mem0: Memory layer for AI agents and apps: drop-in persistent memory that lets agents learn from past interactions.
• Letta: Platform for stateful agents with memory, identity and the ability to learn over time (formerly MemGPT); terminal UI, App Server, desktop app and Agent SDK.

Guides & comparisons

• Memory layers for AI agents (Comparison): Mem0, LangMem, the Claude memory tool, Graphiti, Zep, Cognee and Letta compared on memory model, who writes memories, self-hosting and license, hosted pricing, MCP servers, SDK languages and framework ties.

Sources

• https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool
• https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool.md

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)