Skill

mem0-codex

Integrates Mem0 persistent memory for Claude Code tasks using MCP tools. Retrieves relevant memories on new tasks, stores learnings like decisions and strategies, captures session states.

developer-tools

npx claudepluginhub mem0ai/mem0 --plugin mem0

Popularity

Parent stars

56,038

Parent forks

6,382

Shared by

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/mem0:mem0-codex

User invocable

Model invocable

Inline context

Default effort

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

You have access to persistent memory via the mem0 MCP tools. Follow this protocol to maintain context across sessions.

SKILL.md

63 lines · ~576 tokens

Similar Skills

engram-memory

3.6k

Proactively saves decisions, conventions, bugs, discoveries, and preferences to persistent Engram memory across sessions using mem_save and related tools.

engram

memory-management

Manages persistent memory across Claude Code sessions via AutoMem. Recall project context, architectural decisions, bug fixes, user preferences, and patterns at session start or debugging.

1 file6 tools

automem

memesh

Manages persistent AI memory across coding sessions: remember decisions/patterns, recall context, learn from bugs/mistakes. Auto-triggers on memory prompts, key events like decisions/fixes via Claude Code hooks.

memesh

Stats

LanguagePython

Parent stars56,038

Parent forks6,382

MaintenanceGood

Last CommitApr 2, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Stats

Actions

Help us improve

Share bugs, ideas, or general feedback.

Mem0 Memory Protocol for Codex

You have access to persistent memory via the mem0 MCP tools. Follow this protocol to maintain context across sessions.

On every new task

Call search_memories with a query related to the current task or project to load relevant context.

Review returned memories to understand what has been learned in prior sessions.

If appropriate, call get_memories to browse all stored memories for this user.

After completing significant work

Extract key learnings and store them using the add_memory tool:

Decisions made -> Include metadata {"type": "decision"}

Strategies that worked -> Include metadata {"type": "task_learning"}

Failed approaches -> Include metadata {"type": "anti_pattern"}

User preferences observed -> Include metadata {"type": "user_preference"}

Environment/setup discoveries -> Include metadata {"type": "environmental"}

Conventions established -> Include metadata {"type": "convention"}

Memories can be as detailed as needed -- include full context, reasoning, code snippets, file paths, and examples. Longer, searchable memories are more valuable than vague one-liners.

Before losing context

If context is about to be compacted or the session is ending, store a comprehensive session summary:

## Session Summary ### User's Goal [What the user originally asked for] ### What Was Accomplished [Numbered list of tasks completed] ### Key Decisions Made [Architectural choices, trade-offs discussed] ### Files Created or Modified [Important file paths with what changed] ### Current State [What is in progress, pending items, next steps]

Include metadata: {"type": "session_state"}

Memory hygiene

Do NOT write to MEMORY.md or any file-based memory. Use mem0 MCP tools exclusively.

Only store genuinely useful learnings. Skip trivial interactions.

Use specific, searchable language in memory content.

Mem0 Memory Protocol for Codex

You have access to persistent memory via the mem0 MCP tools. Follow this protocol to maintain context across sessions.

On every new task

Call search_memories with a query related to the current task or project to load relevant context.
Review returned memories to understand what has been learned in prior sessions.
If appropriate, call get_memories to browse all stored memories for this user.

After completing significant work

Extract key learnings and store them using the add_memory tool:

Decisions made -> Include metadata {"type": "decision"}
Strategies that worked -> Include metadata {"type": "task_learning"}
Failed approaches -> Include metadata {"type": "anti_pattern"}
User preferences observed -> Include metadata {"type": "user_preference"}
Environment/setup discoveries -> Include metadata {"type": "environmental"}
Conventions established -> Include metadata {"type": "convention"}

Memories can be as detailed as needed -- include full context, reasoning, code snippets, file paths, and examples. Longer, searchable memories are more valuable than vague one-liners.

Before losing context

If context is about to be compacted or the session is ending, store a comprehensive session summary:

## Session Summary

### User's Goal
[What the user originally asked for]

### What Was Accomplished
[Numbered list of tasks completed]

### Key Decisions Made
[Architectural choices, trade-offs discussed]

### Files Created or Modified
[Important file paths with what changed]

### Current State
[What is in progress, pending items, next steps]

Include metadata: {"type": "session_state"}

Memory hygiene

Do NOT write to MEMORY.md or any file-based memory. Use mem0 MCP tools exclusively.
Only store genuinely useful learnings. Skip trivial interactions.
Use specific, searchable language in memory content.