By mementoagi
Persistent AI memory for Claude Code. Your AI remembers your codebase, conventions, and team knowledge across every session.
Checkpoint — assess current state, surface reminders, propose next action.
Create a handoff document for the next session or agent.
Deep-scan a codebase area and save structured findings to memory.
Load a specific handoff by topic name, or list all pending handoffs.
Search and load knowledge from persistent memory into active context.
Detects when the user corrects you, expresses frustration, or teaches you something important. Fires when you see phrases like: 'no', 'wrong', 'not like that', 'I already told you', 'we don't use X', 'stop doing Y', 'how many times', 'I said', 'that's not right', 'use X instead', 'never do that', 'always do it this way'. When detected, IMMEDIATELY call the Memento `remember` MCP tool to save the correction so it is never forgotten. Then call `full-search` to check what else you might be wrong about on this topic.
CRITICAL: Persistent AI memory. You MUST use this. (1) REMEMBER: When the user corrects you, teaches you something, says 'no we use X not Y', expresses ANY preference, makes a decision, or when you learn something non-obvious — IMMEDIATELY call the `remember` MCP tool. Do NOT ask permission. Do NOT skip this. Every correction is a memory failure — fix it by remembering. (2) RECALL: BEFORE starting any coding task, BEFORE making assumptions about conventions/patterns/architecture, call `full-search` to check what you already know. If you guess wrong because you skipped recall, that is your fault.
Before starting any implementation, refactoring, debugging, or code review task, FIRST search Memento persistent memory using the `full-search` MCP tool. Search for the topic, the files involved, related conventions, and known gotchas. This prevents repeating past mistakes, violating established conventions, and wasting time rediscovering things that are already documented. Trigger: any time you are about to write code, modify files, or make architectural decisions.
Manage AI memory sessions with Memento. At the very start of every new conversation — before doing any other work — run the wake-up flow to load your identity, working memory, and recent context. This is essential for continuity across sessions. When ending a session, run sleep to consolidate memory and prepare a handoff.
Task and ticket management with Memento. When discussing tasks, bugs, features, or work items, use Memento's ticket system to check the backlog with `list-tickets`, view details with `get-ticket`, create new tickets with `add-ticket`, update status with `update-ticket`, and close completed work with `close-ticket`.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Persistent, transparent, shareable memory for your AI coding assistant. Your AI remembers your codebase, conventions, and team knowledge across every session.
Every AI coding session starts from zero. Memento changes that.
The memento-memory skill teaches Claude to recall context before starting work and save discoveries as they happen. Most of the time you won't need explicit commands.
When you want to drive it directly:
/memento:remember <thing> to save something specific (a decision, a convention, a gotcha)/memento:recall <topic> to search memory for a topic/memento:wake-up at the start of a session to load your full context| Skill | What it does |
|---|---|
memento-memory | Teaches Claude to proactively save discoveries and recall context before working |
memento-session | Teaches Claude session lifecycle: wake-up to load memory, sleep to consolidate |
memento-tickets | Teaches Claude to use the ticket system for task tracking |
| Event | Action |
|---|---|
SessionStart | Reminds Claude to run wake-up and load memory |
| Agent | What it does |
|---|---|
memento-coder | Memory-powered coding agent that recalls context before working and saves discoveries |
The plugin works alongside the Memento Cloud MCP server, which you register at the user level via claude mcp add (one-time setup — see step 2 below). The plugin does not bundle its own MCP server registration.
Sign up at mementoagi.com.
Get your API key from mementoagi.com/dashboard/getting-started. The Getting Started page provides a one-line claude mcp add command with your key embedded — paste it into your terminal:
claude mcp add --transport stdio --env MEMENTO_API_KEY=<your-key> memento -- npx -y memento-mcp-client@latest
Verify it connected:
claude mcp list # should show memento ✓ Connected
From inside a Claude Code session:
/plugin marketplace add mementoagi/memento-claude-code-plugin
/plugin install memento@memento-plugins
Or from the terminal:
claude plugin marketplace add mementoagi/memento-claude-code-plugin
claude plugin install memento@memento-plugins
/memento:wake-up
Your AI comes with its own identity. The first session introduces it to you and begins building memory.
| Command | What it does |
|---|---|
/memento:wake-up | Start a session: loads identity, memory, recent context |
/memento:recall | Search and load from memory |
/memento:remember | Save information to persistent memory |
/memento:sleep | End session, consolidate memory |
/memento:sync-commands | Refresh commands after upgrading your tier |
Memento uses the Model Context Protocol (MCP) to connect Claude Code to cloud-hosted persistent memory.
Skills teach Claude behavioral patterns: when to remember, when to recall, how to manage sessions. These are auto-loaded by Claude when relevant to your conversation.
Commands are thin stubs that fetch the latest logic from Memento Cloud at runtime, so your commands are always up to date.
Hooks automate lifecycle events. The SessionStart hook prompts Claude to load your memory at the beginning of each session.
Your AI's memory is stored as transparent markdown files:
For more information, visit mementoagi.com.
npx claudepluginhub mementoagi/memento-claude-code-plugin --plugin mementoHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code