Skip to main content
skill CX Codex

remember · mem0ai — Claude Code skill: what it does, how to install

When you tell the agent to remember something, this skill makes it restate the fact clearly so Mem0 can save it for later sessions in the repository.

Apache-2.0 161 installs ★ 69,319 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mem0ai/mem0 --skill remember -a claude-code
Open on GitHub

What remember does

Mem0 builds memories from the session on its own, with no write command to call. The remember skill works with that. When you ask the agent to remember something, it restates the fact in one or two sentences in its reply, including the names, values or paths the fact depends on. Mem0 reads that visible reply, so a precise restatement decides what gets stored.

The agent then tells you the note is saved along with the session's other memories once the session ends or compacts, and that it will show up in later sessions in the same repository. You can check afterwards with /mem0:search.

The skill writes nothing itself. Memory is created in the background after the session, so you get no record ID and no instant "saved" message, and the skill tells the agent not to invent either one. It also sets disable-model-invocation: true, so the agent won't call it on its own. You trigger it.

What it helps with

  • pin a project agreement for future sessions
  • store a name, value or path that a decision depends on
  • get a precise restatement of a fact that Mem0 can pick up from the reply
  • avoid a made-up record ID or a false "saved" message
  • look up later with /mem0:search what was recorded

Example prompts for the agent

  • Use the remember skill: the staging config lives in config/staging.yaml
  • /remember we deploy only from the release branch
  • Run remember and save this: migrations run before the tests

How to install remember

1Skills CLI (Vercel)

npx skills add mem0ai/mem0 --skill remember -a claude-code

2Manually: put the files in place

~/.claude/skills/remember/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/remember/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about remember

How do I install remember in Claude Code?

Run npx skills add mem0ai/mem0 --skill remember -a claude-code. The skill file ends up at ~/.claude/skills/remember/SKILL.md.

What does remember do?

When you ask the agent to remember a fact, it restates the fact fully and accurately in its reply, and Mem0 builds the memory from that reply. The skill does not write a record itself.

When does the saved note become a memory?

After the session ends or compacts, in the background, so no record ID appears right away. The fact then surfaces in later sessions in this repository, and /mem0:search lets you check it.

Source text

SKILL.md · Apache-2.0
---
name: remember
description: Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
disable-model-invocation: true
---

# Remember something for future sessions

Mem0 creates memories from the session automatically — there is no separate
write command. When the user asks to remember something:

1. Restate the fact clearly and completely in your reply, in one or two
   sentences, including any names, values, or paths it depends on. Your visible
   reply is what memory extraction reads, so a precise restatement is what gets
   remembered.
2. Tell the user it will be saved with this session's memories when the session
   ends or compacts, and that it will surface in future sessions in this
   repository (they can check later with /mem0:search).

Do not invent a storage confirmation or a memory ID — creation happens in the
background after the session.

© mem0ai · Apache-2.0 · mem0ai/mem0

Similar skills

All skills for Agent setup: memory, context, orchestration →

remember by other authors comes first.

remember rohitg00 remember saves insights, decisions, and learnings to agentmemory long-term storage with concept tags so agents can retrieve them later. CX Codex +1 15,000installs remember official github remember turns lessons from coding sessions into domain-based memory instructions for GitHub Copilot. Useful when project guidance must persist across VS Code contexts. CX Codex +1 9,248installs remember langchain-ai Reads back through the conversation and saves best practices and agreed rules to AGENTS.md or a new skill. Fires on phrases like "remember this" and "update memory". CX Codex +1 236installs remember Yeachan-Heo remember is a Claude Code skill that sorts session knowledge into the right place. It activates when useful findings need to be preserved or organized. CX Codex +1 695installs remember Alireza Rezvani remember saves key debugging findings and team conventions directly into project auto-memory. Useful when critical context must persist across Claude Code sessions. CX Codex +1 1,661installs conversation-memory sickn33 Provides architectural patterns for tiered conversation memory in LLM apps, spanning session buffers and entity stores. Useful when building persistent context across user dialogs. CX Codex +1 1,600installs qdrant-memory cnkang This skill for Claude Code works with persistent Qdrant memory through MCP tools or a standalone CLI. It handles recall, record edits, maintenance, and migration. CX Codex +1 999installs DeepMem deepmemteam DeepMem is an MCP server for Claude Code that gives agents persistent memory, storing facts once and retrieving them by meaning across sessions. CX Codex +1 ★ 114repo stars agentmemory-architecture rohitg00 agentmemory-architecture — a skill that explains the internals of agentmemory: the iii engine, storage model, ports, and viewer. It kicks in when you reason about how memory flows end to end or extend the system. CX Codex +1 11,700installs how-it-works thedotmack how-it-works — a skill for Claude Code and Codex explains how claude-mem stores observations, injects past context, and retains data locally. Answers questions about background memory tracking across sessions. CX Codex +1 5,600installs hermes-history-ingest Ar9av hermes-history-ingest — a skill for Claude Code, Codex, Cursor and other platforms that turns Hermes agent history into Obsidian wiki pages. Extracts patterns from memory files and session logs, groups them by topic and project. CX Codex +1 2,500installs

From the same set10

The whole set →
mem0-cli The mem0-cli skill lets an agent use Mem0 memory operations from a terminal, including adding, searching, reading, updating, and deleting records. CX Codex +1 836installs mem0-vercel-ai-sdk mem0-vercel-ai-sdk connects Mem0 memory to the Vercel AI SDK. It shows your agent how to retrieve and store context inside generateText and streamText calls. CX Codex +1 552installs mem0-integrate mem0-integrate wires Mem0 memory into an existing backend repository via a TDD pipeline. Sets up a feature branch, writes tests first, and guards new logic behind a flag. CX Codex +1 441installs mem0-test-integration mem0-test-integration is a skill that verifies a Mem0 integration created by /mem0-integrate by installing dependencies, running tests and a live smoke flow, then printing a scorecard. CX Codex +1 358installs mem0-oss-to-platform mem0-oss-to-platform moves a project from the local mem0 SDK to the hosted Platform SDK, with a reviewable plan before any migration changes are made. CX Codex +1 214installs forget This skill removes Mem0 memories for a user and repository. Use it when you want an agent to clear or forget stored memories. CX Codex +1 155installs context-loader context-loader is a Claude Code skill that searches project memories for code details, decisions, and commands. It surfaces earlier work relevant to the current task. CX Codex +1 117installs mem0 mem0 adds persistent memory to Claude Code so your agent retains project context across terminal sessions. ★ 69,319repo stars

Project sponsors

Companies that keep this analytics open