remember Skill (agentmemory) for Claude Code: Save Notes

Saves a decision, fact or lesson to agentmemory long-term storage, with searchable tags, for anyone who wants Claude to remember across sessions.

Installs: 14.3K; on skills.sh
Stars: 30.1K; on GitHub
Files: 2; besides SKILL.md
Updated: Oct 2026; last repo commit

remember is the save command of the agentmemory plugin. You type /remember with the thing to keep, and Claude pulls out the core fact, picks 2 to 5 specific lowercase tags, adds any file paths, and calls the memory_save tool. It then repeats the tags back so you know what to search for later.

It triggers on phrases like "remember this", "save this", "note that" and "don't forget". It bundles no scripts, but it needs the agentmemory server running and its MCP tools connected. Pair it with recall to read memories back and forget to remove them.

Good for

Developers who want Claude to keep project decisions between sessions
Teams already running agentmemory across several coding agents
Anyone who says "remember this" and expects it to stick

Install remember

Claude Code

Copy this prompt.

Install the remember skill in Claude Code. Run this command:

npx -y @agentmemory/agentmemory@latest

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js 20 or newer.

This skill only works when the memory server is running and the agentmemory MCP tools are connected. The plugin route is the one the README recommends for Claude Code. The skills-only route installs all 17 skills but does not connect the MCP tools by itself. Pick one route, not both.

From the project README. Source.

What's in the skill

When it loads

Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags. Use when the user says "remember this", "save this", "note that", "don't forget", or wants to preserve knowledge for future sessions.

Sections in SKILL.md

Quick start
Why
Workflow
Anti-patterns
Checklist
See also
Troubleshooting

Key facts

Author: rohitg00
Repository: rohitg00/agentmemory
Installs on skills.sh: 14,335 as of 2026-11-02
GitHub stars: 30,069 for the whole rohitg00/agentmemory repo
License: Apache-2.0 (repo and plugin.json)
Last repo commit: 2026-10-29
What is inside: 3 files including SKILL.md: SKILL.md, EXAMPLES.md and TROUBLESHOOTING.md. It bundles no scripts.
Part of: The agentmemory plugin (17 skills, 12 hooks, 54 MCP tools per plugin.json)
Needs: The agentmemory server running, and its memory_save tool connected

What it includes

Slash command that saves your text to long-term memory
The command takes your text as its argument and saves it with the memory_save tool.
Try: “/remember We rotate JWT refresh tokens on every use; the old token is revoked server-side in auth/refresh.ts.”
Write · /remember [what to remember]
Stores content, concept tags and file paths
Takes the content, a comma-separated list of concepts and a comma-separated list of files. In a multi-agent setup it also takes an agentId so the memory lands in the right agent scope.
Write · memory_save
2 to 5 lowercase concepts, specific over generic
jwt-refresh-rotation is a good tag and auth is too broad. Tags such as stuff, code and notes are listed as the wrong pattern.
Pick specific tags
Saves your phrasing, not a paraphrase
The checklist asks for your own words and real file paths, not guesses.
Keep your wording
A corrected fact replaces the old record in search
Near-duplicate content supersedes the old record. The old one leaves recall but stays in the version chain.
Write · Update by saving again
Steps for when memory_save is not available
Points to checks for the MCP connection, the daemon status, and a REST fallback on port 3111.
TROUBLESHOOTING.md

From the official docs

Permissions

Medium risk

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

The plugin records your sessions through hooks
The README lists captured data: user prompts (privacy-filtered), tool name, input and output, errors, and the assistant reply of each turn. Review what is stored in the viewer, and use the forget skill to remove entries. github.com
Installing starts a local server and runs npm code
The setup command pulls the latest package with npx and starts a background server. On macOS and Linux it also needs curl, sh and tar for automatic runtime setup. github.com
Saved memories flow back into later sessions
plugin.json says the plugin injects context into future sessions. In the hook scripts, SessionStart and PreToolUse inject context only when AGENTMEMORY_INJECT_CONTEXT=true, as the README also says. The PreCompact script asks the server for context before each compaction with a default budget of 1500 and prints it as hook output; AGENTMEMORY_PRE_COMPACT_BUDGET=0 turns that off. Our advice: avoid saving text you do not trust, because the assistant reads it back. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only switch is documented for these skills.
Talks to	The server and viewer bind to loopback (127.0.0.1) by default. Compression or embeddings with a provider you configure use that provider. Local semantic search downloads an embedding model on first use if you set EMBEDDING_PROVIDER=local
Sign-in and keys	A local server creates a random secret at ~/.agentmemory/secret with mode 0600 and the bundled clients read it. A remote server needs AGENTMEMORY_SECRET in your environment.
Data retention	Memories are stored on your machine in the agentmemory data folder until you delete them. The README says API keys, bearer tokens and <private> tags are stripped before storage.
Scopes	The Claude Code plugin registers 12 hooks that run node scripts on events such as every prompt, every tool call and the end of each turn The plugin ships a .mcp.json that starts a node bridge to the local memory server Setup runs npx -y @agentmemory/agentmemory@latest, writes config to ~/.agentmemory and starts a server on localhost:3111 If the MCP tools are missing, the skill's TROUBLESHOOTING.md tells the assistant to call the REST API on the daemon directly with a bearer secret, read from AGENTMEMORY_SECRET or, for loopback URLs, from ~/.agentmemory/.env and ~/.agentmemory/secret

Questions

What does the remember skill do?

It saves one insight, decision or fact to agentmemory so a later session can find it. Claude adds 2 to 5 concept tags and any file paths, then tells you which tags it used.

How do I install remember?

Use the install box at the top of this page. Start the agentmemory server first, then add the plugin, because the skill calls tools that the server provides. Installing the skill folder alone is not enough.

Does it work without the agentmemory server?

No. The skill calls memory_save, which comes from the agentmemory MCP connection. Its troubleshooting file explains what to check when that tool is missing.

Does it need an API key?

The README says keyword search works without one in keyless mode. Keys are only for optional LLM compression or semantic search with a provider. A local server makes its own secret.

How do I read back or delete what I saved?

Use recall to search memories and forget to delete them. Both are skills in the same plugin, and the remember file lists them as its pair.

Is remember safe?

It writes text you give it to a memory store on your machine. The setup around it is larger than the skill: the plugin adds hooks that record sessions and runs a local server. See the safety section on this page before installing.

Information

updated Nov 2, 2026

Repository: rohitg00/agentmemory
Folder: plugin/skills/remember

rohitg00/agentmemory skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 10

rohitg00/agentmemory README · github.com
skills CLI commands · github.com
remember SKILL.md · github.com
Shared TROUBLESHOOTING.md · github.com
plugin .mcp.json · github.com
plugin.json · github.com
pre-compact.mjs · github.com
TROUBLESHOOTING.md · github.com
session-start.mjs · github.com
plugin hooks.json · github.com