Memori

Memori is an AI Engineering skill for Claude Code, published by MemoriLabs in Memori.

15.9K stars3K forkson MemoriLabs/MemoriAdded 2026/08/14+1% in starsRepository updated 2026/08/13

agentagent-memoryagenticaiaiai-memoryclaude-codeenterprisehermesllmlong-short-term-memorymemorymemory-managementopenclawpythonragstate-managementstatefultypescript

Install in seconds

Install Memori

Copy Memori into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/MemoriLabs/Memori/tree/main/integrations/claude-code ~/.claude/skills/claude-code

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/MemoriLabs/Memori.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: integrations/claude-code/SKILL.md in MemoriLabs/Memori
Installs to: ~/.claude/skills/claude-code
Collection: One of 4 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Memori does

Memori adds ambient long-term memory to Claude Code by checking recall before every substantial response and storing the final exchange afterward. Use it to retain preferences, decisions, constraints, and project context across sessions.

Memori is cataloged under AI Engineering on DirSkills. Memori comes from a repository tagged agent, agent-memory, agenticai, ai and ai-memory.

Documentation

README

Excerpt

Memori Claude Code Skill

Thin CLI wrapper around Memori Cloud for Claude Code subprocesses. Memori is an ambient memory enhancement, not an explicit destination tool. Do not wait for the user to ask to "use Memori" before applying the memory lifecycle below. Claude Code's primary job remains answering the user, editing code, debugging, reviewing, and completing the requested work.

Run commands from the Claude Code integration root:

bun .claude/skills/memori/index.ts <command> [--flags ...]

Flags accept --flag value or --flag=value.

Setup

Configure credentials in .claude/settings.local.json (per-project, not checked into source control). Claude Code injects everything under env into every Bash subprocess, including this skill:

This is the opening of the README. Read the full README on GitHub.

Commands Memori provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/clear

Frequently asked about Memori

What else does MemoriLabs publish alongside Memori?
Memori is one of 4 skills that DirSkills catalogs from MemoriLabs/Memori, the repository it ships in. Its siblings there include Memori, Memori and Memori MCP Usage. Each one is a separate skill with its own page in this directory, installs the same way Memori does, and is maintained by MemoriLabs in that same repository. The rest of the collection is listed on the MemoriLabs/Memori page.
How does Memori compare to other AI Engineering skills?
Memori ranks #286 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Memori against them. Open each page to compare what they document and how they install.