LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Toolofficial publisher

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.

Overall score
6.5 /10
Security: one caveat, see the card
Utility
7.0
Reliability
6.0
Security
One caveat
Ease
5 min · Technical

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)

1. Obtain an Anthropic API key at platform.claude.com. 2. Install the SDK for your language (for example: pip install anthropic in Python). 3. Add the entry {"type": "memory_20250818", "name": "memory"} to the tools array in your request. 4. Implement a client-side handler that executes the view, create, str_replace, insert, delete and rename commands against your storage. 5. In that handler, reject any operation whose path falls outside the /memories directory (path traversal protection). 6. Use BetaLocalFilesystemMemoryTool (Python/TypeScript) or refer to the SDK examples for your language to get started quickly.
pip install anthropic

Official documentation ↗

In the same category

Whole category Feed (memory, context) →