mem0 CLI (Python)

The official command-line interface for mem0 — the memory layer for AI agents. Python implementation.

Built for AI agents. Pass --agent (or --json) as a global flag on any command to get structured JSON output optimized for programmatic consumption — sanitized fields, no colors or spinners, and errors as JSON too.

Prerequisites

• Python 3.10+

Installation

Using pipx (recommended)

pipx install mem0-cli

Using pip

pip install mem0-cli

Note: On macOS with Homebrew Python, pip install outside a virtual environment will fail with an externally-managed-environment error (PEP 668). Use pipx instead, or install inside a virtual environment.

Quick start

# Interactive setup wizard
mem0 init

# Or login via email
mem0 init --email alice@company.com

# Or authenticate with an existing API key
mem0 init --api-key m0-xxx

# Add a memory
mem0 add "I prefer dark mode and use vim keybindings" --user-id alice

# Search memories
mem0 search "What are Alice's preferences?" --user-id alice

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

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

# Update a memory
mem0 update <memory-id> "I switched to light mode"

# Delete a memory
mem0 delete <memory-id>

Commands

mem0 init

Interactive setup wizard. Prompts for your API key and default user ID.

mem0 init
mem0 init --api-key m0-xxx --user-id alice
mem0 init --email alice@company.com

If an existing configuration is detected, the CLI asks for confirmation before overwriting. Use --force to skip the prompt (useful in CI/CD).

mem0 init --api-key m0-xxx --user-id alice --force

mem0 add

Add a memory from text, a JSON messages array, a file, or stdin.

mem0 add "I prefer dark mode" --user-id alice
mem0 add --file conversation.json --user-id alice
echo "Loves hiking on weekends" | mem0 add --user-id alice

mem0 search

Search memories using natural language.

mem0 search "dietary restrictions" --user-id alice
mem0 search "preferred tools" --user-id alice --output json --top-k 5

mem0 list

List memories with optional filters and pagination.

mem0 list --user-id alice
mem0 list --user-id alice --category preferences --output json
mem0 list --user-id alice --after 2024-01-01 --page-size 50

mem0 get

Retrieve a specific memory by ID.

mem0 get 7b3c1a2e-4d5f-6789-abcd-ef0123456789
mem0 get 7b3c1a2e-4d5f-6789-abcd-ef0123456789 --output json

mem0 update

Update the text or metadata of an existing memory.

mem0 update <memory-id> "Updated preference text"
mem0 update <memory-id> --metadata '{"priority": "high"}'
echo "new text" | mem0 update <memory-id>

mem0 delete

Delete a single memory, all memories for a scope, or an entire entity.

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

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

# Delete all memories project-wide
mem0 delete --all --project --force

# Preview what would be deleted
mem0 delete --all --user-id alice --dry-run

mem0 import

Bulk import memories from a JSON file.

mem0 import data.json --user-id alice

The file should be a JSON array where each item has a memory (or text or content) field and optional user_id, agent_id, and metadata fields.

mem0 config

View or modify the local CLI configuration.

mem0 config show              # Display current config (secrets redacted)
mem0 config get api_key       # Get a specific value
mem0 config set user_id bob   # Set a value

mem0 entity

List or delete entities (users, agents, apps, runs).

mem0 entity list users
mem0 entity list agents --output json
mem0 entity delete --user-id alice --force

mem0 event

Inspect background processing events created by async operations (e.g. bulk deletes, large add jobs).

# List recent events
mem0 event list

# Check the status of a specific event
mem0 event status <event-id>

mem0 status

Verify your API connection and display the current project.

mem0 status

Agent mode

Pass --agent (or its alias --json) as a global flag on any command to get output designed for AI agent tool loops:

mem0 --agent search "user preferences" --user-id alice
mem0 --agent add "User prefers dark mode" --user-id alice
mem0 --agent list --user-id alice
mem0 --agent delete --all --user-id alice --force

Every command returns the same envelope shape:

{
  "status": "success",
  "command": "search",
  "duration_ms": 134,
  "scope": { "user_id": "alice" },
  "count": 2,
  "data": [
    { "id": "abc-123", "memory": "User prefers dark mode", "score": 0.97, "created_at": "2026-01-15", "categories": ["preferences"] }
  ]
}

What agent mode does differently from --output json:

• Sanitized data: only the fields an agent needs (id, memory, score, etc.) — no internal API noise
• No human output: spinners, colors, and banners are suppressed entirely
• Errors as JSON: errors go to stdout as {"status": "error", "command": "...", "error": "..."} with a non-zero exit code

Use mem0 help --json to get the full command tree as JSON — useful for agents that need to self-discover available commands.

Output formats

Control how results are displayed with --output:

Global flags

These flags are available on all commands:

mem0 --version prints the CLI version. It is only valid before a subcommand, not after one.

Environment variables

Environment variables take precedence over values in the config file, which take precedence over defaults.

Development

cd cli/python
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

# Run during development
python -m mem0_cli --help
mem0 add "test memory" --user-id alice

Releasing

1. Update version in pyproject.toml
2. Create a GitHub Release with tag cli-v<version> (e.g. cli-v0.2.1)

For a pre-release, use a beta version like 0.2.1b1 and check the pre-release checkbox.

Documentation

Full documentation is available at docs.mem0.ai/platform/cli.

License

Apache-2.0