Memori
A Claude Code skill that pulls memory from Memori Cloud before every non-trivial answer and writes new facts back to it
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- It sends dialogue facts and context to the Memori Cloud store
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/memoriDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Assembled automatically, review before installing.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a claude-code -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .claude/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .claude/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a cursor -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .agents/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .agents/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a github-copilot -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .github/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .github/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a codex -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .agents/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .agents/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a gemini-cli -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .agents/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .agents/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .devin/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .devin/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Formerly Windsurf.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a cline -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .cline/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .cline/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a roo -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .roo/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .roo/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
A fork of Roo Code, same .roo folders.
Run in a terminal in the project folder
npx skills add memorilabs/memori --skill memori -a opencode -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 574b1ea
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .agents/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .agents/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .agents/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .agents/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/memorilabs/memori.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /integrations/openclaw/skills/memori/
git -C "$tmp" checkout 574b1ea3e876f100ef82c37817d603eb7e258e59
mkdir -p .agents/skills
cp -R "$tmp/integrations/openclaw/skills/memori" .agents/skills/memoriCommands for macOS and Linux, on Windows run them in Git Bash.
Copy the skill into .claude/skills/memori, set MEMORI_API_KEY and MEMORI_ENTITY_ID in .claude/settings.local.json, and the skill is then invoked automatically via bun .claude/skills/memori/index.ts.
Other ways from the author
npm install @memorilabs/memoriTypeScript SDK for direct code integration.
This is third-party code. Review the repository files before installing.
What it does
The memori skill wraps Memori Cloud in a thin CLI call for Claude Code and runs ambiently: before answering a non-trivial question, the agent reaches into memory for relevant context on its own, without waiting to be asked to 'remember'. After answering, it writes new facts and decisions back so they carry over into future sessions and other projects for the same user. Besides the Claude Code skill, Memori has TypeScript and Python SDKs, an MCP integration and an OpenClaw plugin, all talking to the same cloud memory store.
Who it is for. For developers who want Claude Code to remember project decisions and context across sessions without manually re-explaining them.
Good fit when
- You need the agent to remember preferences and past decisions without being reminded
- Work on a project spans a long time and context accumulates session by session
- You need one memory shared across several integrations: Claude Code, MCP, OpenClaw
Not a fit when
- The project is one-off and there is no reason to persist context between sessions
- You cannot set up a Memori Cloud account and API key
Example request
Use Memori to recall which architecture decision we made for this module last timeLimitations
The skill is a thin client to Memori Cloud, so it needs a cloud API key and a stable user identifier. Self-hosting is possible via the open Rust core with Node and Python bindings, but it requires a separate database infrastructure.
How to disable. Remove the memori folder from .claude/skills, or remove MEMORI_API_KEY from .claude/settings.local.json so the skill stops being invoked.
Security check
- It sends dialogue facts and context to the Memori Cloud store
README in short
The README describes Memori as LLM- and datastore-agnostic agent memory infrastructure that turns agent execution and conversation into structured, persistent state. It shows SDK installs via npm and pip and a quick start through Memori Cloud with a single API key. The repo includes integrations: a SKILL.md for Claude Code, an MCP skill in the cloud docs, and an OpenClaw plugin with two skills.
SKILL.md
--- name: memori description: > Ambient Memori long-term memory for Claude Code via local Bash. MUST TRIGGER on essentially every non-trivial user turn: run recall before drafting any substantive response, whether or not the user mentioned memory, a prior session, or past work. The default is to check memory first; do not wait to be asked. Always fire before external lookups (WebSearch/WebFetch) and before answering any question about preferences, prior decisions, constraints, project history, status, past work, or any non-trivial coding/research task. Skip only for trivial acknowledgements/closings, purely self-contained turns where prior context cannot possibly help, or when the user explicitly opts out. argument-hint: '<command> [--flags ...]' allowed-tools: Bash --- # 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.
FAQ
Do I need to explicitly ask the agent to remember something?
No, the skill is described as triggering on almost every non-trivial turn; the agent checks memory before answering on its own.
Can it be used outside Claude Code?
Yes, there are TypeScript and Python SDKs, an MCP skill and an OpenClaw plugin on top of the same cloud store.
Related
Open-source personal AI assistant on your own machine: answers in Telegram, Slack, Discord and WhatsApp, extended with skills and plugins
A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself
An open source coding agent for the terminal and desktop with build and plan modes
Open prompt library with a Claude Code plugin, MCP server and CLI: search, fetch and improve prompts and skills from an agent