Terminal
Terminal/Skill
Command-line tool for Mem0 memory: add, search, list, update and delete memories from a terminal, scripts or CI.
By Mem0
Works with
npx skills add mem0ai/mem0 --skill mem0-cliThe 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.
Node.js (npm):
npm install -g @mem0/cli
Python (pip):
pip install mem0-cli
Both packages install a mem0 binary with the same commands, options, and output formats (see Node and Python Differences for the exceptions).
Autonomous Mem0 setup for agents (no email, no dashboard):
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):
mem0 init
Or set the environment variable directly:
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
mem0 add "I prefer dark mode" --user-id alice
mem0 search "preferences" --user-id alice
mem0 list --user-id alice
mem0 get <memory-id>
mem0 update <memory-id> "new text"
mem0 delete <memory-id>
mem0 delete --all --user-id alice --force
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:
{
"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:
{
"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.
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.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.Search query cannot be empty. in Python, No query provided... in Node) and the delete dry-run footers differ slightly.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 delete --entity -u alice deletes the entity itself AND all its memories (cascade). These are mutually exclusive modes.--dry-run in --json/--agent mode: mem0 --json delete --all --dry-run still requires --force, then prints nothing and deletes nothing (exit 0). Node also prints nothing for single and --entity dry runs. Use text mode to see the preview.--dry-run does not protect --all --project: mem0 delete --all --project --dry-run ignores the flag and deletes every memory in the project. Never use --dry-run to preview a project-wide delete.--user-id), the CLI uses ONLY the explicit IDs and ignores config defaults. If no scope flags are given, all configured defaults apply.add, search, and update. In --json/--agent mode add never reads stdin (Python also skips it for search and update), so pass the text as an argument there.Load these on demand for deeper detail:
| Topic | File |
|---|---|
| Command reference (all commands, flags, options, examples) | references/command-reference.md |
| Configuration (config file, env vars, precedence, init wizard) | references/configuration.md |
| Workflows (piping, scripting, CI/CD, agent mode recipes) | references/workflows.md |