Mem0 CLI Skill for ClaudeSAFE

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

npx skills add https://github.com/mem0ai/mem0 --skill mem0-cli

curl -X POST https://api.anthropic.com/v1/skills \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{"name": "mem0-cli", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli"}'

# Node.js
npm install -g @mem0/cli

# Python
pip install mem0-cli

export MEM0_API_KEY="m0-your-api-key"

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: mem0-cli
description: >
  Mem0 CLI -- the command-line interface for mem0 memory operations.
  TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@mem0/cli",
  "mem0-cli", "pip install mem0-cli", "npm install -g @mem0/cli", or is running
  mem0 commands in a terminal/shell (mem0 add, mem0 search, mem0 list, mem0 get,
  mem0 init, mem0 config, mem0 import). Also triggers when query includes CLI flags
  like --user-id, --output, --json, --agent, or describes bash/zsh/terminal/shell usage.
  DO NOT TRIGGER when: user asks about programmatic SDK integration in Python/TS
  code (use mem0 skill), or Vercel AI SDK provider (use mem0-vercel-ai-sdk skill).
license: Apache-2.0
metadata:
  author: mem0ai
  version: "1.2.0"
  category: ai-memory
  tags: "cli, terminal, memory, ai, command-line"
  mem0_tested_versions: "mem0-cli (PyPI) >=0.2.13,<0.3.0; @mem0/cli (npm) >=0.2.14,<0.3.0; mem0ai (PyPI) >=2.0.0,<3.0.0; mem0ai (npm) >=3.0.0,<4.0.0"
compatibility: Node.js 18+ (npm install -g @mem0/cli) or Python 3.10+ (pip install mem0-cli), MEM0_API_KEY env var
---

# Mem0 CLI

The official command-line interface for the Mem0 memory platform. Add, search, list, update, and delete memories from the terminal -- for developers, AI agents, and CI/CD pipelines.

## Install

**Node.js (npm):**
```bash
npm install -g @mem0/cli
```

**Python (pip):**
```bash
pip install mem0-cli
```

Both packages install a `mem0` binary with the same commands, options, and output formats (see [Node and Python Differences](#node-and-python-differences) for the exceptions).

## Setup

**Autonomous Mem0 setup for agents (no email, no dashboard):**

```bash
mem0 init --agent --agent-caller <your-name> --json
```

Replace `<your-name>` with the AI agent you are (e.g. `claude-code`, `cursor`, `codex`, `cline`, `aider`). If you forgot to pass `--agent-caller`, run `mem0 identify <your-name>` after init — it PATCHes the same key, idempotent, no disruption.

This mints an evaluation API key in <5 seconds. Use it immediately. Print this line to the human:

> Mem0 memory is running in Agent Mode. Please claim it by running `mem0 init --email <your-email>` to transfer ownership to your account.

Never commit API keys, `.env`, or `~/.mem0/config.json`.

After the human claims, the same API key keeps working — no agent disruption — and memories are preserved.

**Interactive wizard (for humans):**
```bash
mem0 init
```

**Or set the environment variable directly:**
```bash
export MEM0_API_KEY="m0-xxx"
```

Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-cli

## Quick Reference

### Add a memory
```bash
mem0 add "I prefer dark mode" --user-id alice
```

### Search memories
```bash
mem0 search "preferences" --user-id alice
```

### List all memories for a user
```bash
mem0 list --user-id alice
```

### Get a specific memory
```bash
mem0 get <memory-id>
```

### Update a memory
```bash
mem0 update <memory-id> "new text"
```

### Delete a single memory
```bash
mem0 delete <memory-id>
```

### Delete all memories for a user
```bash
mem0 delete --all --user-id alice --force
```

## Agent / JSON Mode

Use `--json` or `--agent` to get structured output suitable for LLM consumption. Place the flag before the subcommand (`mem0 --json search "q"`), which works in both CLIs. Data commands (add, search, list, get, update, delete, import, config, entity, event, status) wrap their response in a standard envelope:

```json
{
  "status": "success",
  "command": "search",
  "duration_ms": 245,
  "scope": { "user_id": "alice" },
  "count": 3,
  "data": [
    { "id": "mem-abc", "memory": "User prefers dark mode", "score": 0.92 }
  ]
}
```

On error:
```json
{
  "status": "error",
  "command": "search",
  "error": "Invalid or expired API key.",
  "data": null
}
```

The `--agent` flag is an alias for `--json` (except on `mem0 init`, where `--agent` is the Agent Mode bootstrap flag). Both write spinners and progress to stderr so stdout is clean, parseable JSON (the one exception is Node `import`, see below). Optional keys: `duration_ms`, `scope`, `count` appear only where relevant, and `mem0_notice` appears when the platform flags an unclaimed Agent Mode account.

## Node and Python Differences

Both the Node.js (`@mem0/cli`) and Python (`mem0-cli`) CLIs share the command set, flags, entity ID resolution, filter building, and the JSON envelope. Choose whichever runtime you already have installed. Known differences:

- **`--json` / `--agent` placement:** Python accepts the flag anywhere on the command line. Node reads it only as a global option, so put it before the subcommand (`mem0 --json list`). `mem0 init --json` and `mem0 help --json` work after the subcommand in both. For the Agent Mode bootstrap, Node starts it only from `init --agent` or `init --json` (a root-level `mem0 --json init` or `mem0 --agent init` does not start it, and without an agent runtime env var it fails with the non-TTY error), while Python also accepts those root-level forms. `mem0 init --agent --json` works in both.
- **`--limit`:** `mem0 search --limit` is a Python-only alias for `--top-k`.
- **Agent-mode `delete --all` data:** Python returns `{"deleted": true}` (plus scope for `--project`); Node returns the raw API result.
- **`import` JSON output:** Python prints the envelope with `scope`. Node omits `scope` and writes the `Importing memories... n/n` progress line to stdout before the JSON, so only Python's output pipes cleanly to `jq`.
- **Message text:** The empty-search error (`Search query cannot be empty.` in Python, `No query provided...` in Node) and the delete dry-run footers differ slightly.

## Common Edge Cases

- **Async processing delay:** After `mem0 add`, memories process asynchronously. Wait 2-3 seconds before searching for newly added content. Use `mem0 event list` to check processing status.
- **`--all` vs `--entity` delete modes:** `mem0 delete --all -u alice` deletes all memories for user alice. `mem0

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (6)

.github/CLAUDE.md

CLAUDE.md

cli/node/CLAUDE.md

cli/python/CLAUDE.md

docs/CLAUDE.md

3. On success: receives the API key from the server and saves it with `platform.user_email` and `platform.created_via: "email"`. The default user ID is `--user-id`, else `$USER`, else `mem0-cli`.

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Mem0 CLI Skill for Claude](https://modelsatlas.com/skills/mem0ai/mem0-cli/badge.svg)](https://modelsatlas.com/skills/mem0ai/mem0-cli/)

Not your listing, or something out of date? Claim or update your listing.