memory (Anthropic)
Tool : A precise action the AI can call · requires anthropic-api
Persistent Claude memory stored in files you host.
Simple and transparent: the memory is readable and deletable.
Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.
What it does, concretely
When a conversation ends, Claude forgets everything that was discussed. The memory tool solves this by letting Claude store information in files hosted by your application, and read them back in future sessions.
In practice, Claude sends read and write requests to a /memories directory. Your application receives these requests, executes them against storage you control (local files, a database, cloud storage) and returns the result to Claude. Claude can then create, read, update and delete files across sessions, without loading all context at once.
This tool is aimed at developers building agents or conversational applications via the Anthropic API who need continuity across sessions: project tracking, user preference retention, or progressively building a knowledge base.
It is not suited for non-technical users: integrating it requires writing code to handle the tool-use loop and file storage. There is no ready-made version accessible without development.
What it offers
- ·Reads the memory directory at the start of each task to retrieve relevant context.
- ·Creates memory files to record new information across sessions.
- ·Targeted editing of existing files via text replacement or insertion at a specific line.
- ·Deletion of files or entire directories to remove outdated information.
- ·Renaming and moving files within the memory directory.
- ·Compatible with multiple storage backends: local filesystem, database, cloud storage, or encrypted files.
- ·Helpers available in Python, TypeScript, C#, Java, PHP and Ruby SDKs to simplify integration.
In practice
- Price
- Free
- Commercial use
- Commercial use: yes
- Available on
- api
- Host
- anthropic-api
- FR interface
- No
Security and data
- Rating
- Security: one caveat, see the card
- Capabilities
- readswritesexecutesnetwork
- Your data
- Data stays local
- Maintenance
- Active
Links and repository checked on 25 October 2026 · added on 1 August 2025
How to install memory (Anthropic)
pip install anthropic