Mem0 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

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

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

skills/mem0/
├── SKILL.md                    # Skill definition and instructions
├── README.md                   # This file
├

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
description: >
  Mem0 Platform SDK for adding persistent memory to AI applications.
  TRIGGER when: user mentions "mem0", "MemoryClient", "memory layer",
  "remember user preferences", "persistent context", "personalization",
  or needs to add long-term memory to chatbots, agents, or AI apps.
  Covers Python SDK (mem0ai), TypeScript SDK (mem0ai), and framework integrations
  (LangChain, CrewAI, OpenAI Agents SDK, Pipecat, LlamaIndex, AutoGen, LangGraph).
  Also covers the open-source self-hosted Memory class.
  This is the DEFAULT mem0 skill for ambiguous queries.
  DO NOT TRIGGER when: user asks about CLI commands, terminal usage, or shell
  scripts (use mem0-cli), or Vercel AI SDK / @mem0/vercel-ai-provider / createMem0
  (use mem0-vercel-ai-sdk).
license: Apache-2.0
metadata:
  author: mem0ai
  version: "3.1.0"
  category: ai-memory
  tags: "memory, personalization, ai, python, typescript, vector-search"
  mem0_tested_versions: "mem0ai (PyPI) >=2.0.0,<3.0.0; mem0ai (npm) >=3.0.0,<4.0.0"
compatibility: Requires Python 3.10+ or Node.js 18+, pip install mem0ai or npm install mem0ai, MEM0_API_KEY env var (Platform), and internet access to api.mem0.ai. Targets the v3 API (Python mem0ai 2.x, TypeScript mem0ai 3.x).
---

# Mem0 Platform Integration

> **Skill Graph:** This skill is part of the Mem0 skill graph:
> - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript)
> - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface
> - **[mem0-vercel-ai-sdk](../mem0-vercel-ai-sdk/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)) -- Vercel AI SDK provider

Mem0 is a managed memory layer for AI applications. It stores, retrieves, and manages user memories via API — no infrastructure to deploy. For self-hosted usage, see the OSS section in the client references below.

## Step 1: Install and authenticate

**Python:**
```bash
pip install mem0ai
export MEM0_API_KEY="m0-your-api-key"
```

**TypeScript/JavaScript:**
```bash
npm install mem0ai
export MEM0_API_KEY="m0-your-api-key"
```

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

> **Don't have a `MEM0_API_KEY`?** Run `mem0 init --agent --agent-caller <your-name> --json` (after `pip install mem0-cli` or `npm install -g @mem0/cli`), substituting your agent identity (e.g. `claude-code`, `cursor`). If you forgot to pass `--agent-caller`, run `mem0 identify <your-name>` after init. The human can claim later with `mem0 init --email <your-email>`.

## Step 2: Initialize the client

**Python:**
```python
from mem0 import MemoryClient
client = MemoryClient(api_key="m0-xxx")
```

**TypeScript:**
```typescript
import MemoryClient from 'mem0ai';
const client = new MemoryClient({ apiKey: 'm0-xxx' });
```

For async Python, use `AsyncMemoryClient`.

## Step 3: Core operations

Every Mem0 integration follows the same pattern: **retrieve → generate → store**.

### Add memories
```python
messages = [
    {"role": "user", "content": "I'm a vegetarian and allergic to nuts."},
    {"role": "assistant", "content": "Got it! I'll remember that."}
]
client.add(messages, user_id="alice")
```

### Search memories
```python
results = client.search("dietary preferences", filters={"user_id": "alice"})
for mem in results.get("results", []):
    print(mem["memory"])
```

### Get all memories
```python
all_memories = client.get_all(filters={"user_id": "alice"})
```

### Update a memory
```python
client.update("memory-uuid", text="Updated: vegetarian, nut allergy, prefers organic")
```

### Delete a memory
```python
client.delete("memory-uuid")
client.delete_all(user_id="alice")  # delete all for a user
```

## Common integration pattern

```python
from mem0 import MemoryClient
from openai import OpenAI

mem0 = MemoryClient()
openai = OpenAI()

def chat(user_input: str, user_id: str) -> str:
    # 1. Retrieve relevant memories
    memories = mem0.search(user_input, filters={"user_id": user_id})
    context = "\n".join([m["memory"] for m in memories.get("results", [])])

    # 2. Generate response with memory context
    response = openai.chat.completions.create(
        model="gpt-5-mini",
        messages=[
            {"role": "system", "content": f"User context:\n{context}"},
            {"role": "user", "content": user_input},
        ]
    )
    reply = response.choices[0].message.content

    # 3. Store interaction for future context
    mem0.add(
        [{"role": "user", "content": user_input}, {"role": "assistant", "content": reply}],
        user_id=user_id
    )
    return reply
```

## Common edge cases

- **Search returns empty:** `add()` is asynchronous and returns `{"event_id": "...", "status": "PENDING"}` (`eventId` on the TS client). Memories are searchable once the event is `SUCCEEDED` (poll `GET /v1/event/{event_id}/`, or wait a few seconds). `infer=False` is synchronous. Also verify `user_id` matches exactly (case-sensitive) and use `filters={"user_id": "..."}` syntax.
- **AND filter with user_id + agent_id returns empty:** Entities are stored separately. Use `OR` instead, or query separately.
- **Duplicate memories:** Don't mix `infer=True` (default) and `infer=False` for the same data. Stick to one mode.
- **Wrong import:** For the hosted Platform use `from mem0 import MemoryClient` (or `AsyncMemoryClient` for async). `from mem0 import Memory` is the self-hosted OSS class and does not use `MEM0_API_KEY`.
- **v3 defaults (Platform):** `top_k=10`, `rerank=False`. `threshold` is a server-side cutoff applied before score blending, not a floor on the returned `score` (the default and `0.0` return the same or nearly the same results). The client sends none of these unless you pass them. The OSS `Memory.search()` default is `top_k=20`. Adjust as needed for your use case.

## v2 Compatibility

The "v2" line is Python SDK 1.x and TypeScript SDK 2.x. If you are still on it, n

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

declared (4 observation(s))

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (7)

.github/CLAUDE.md

CLAUDE.md

cli/node/CLAUDE.md

cli/python/CLAUDE.md

docs/CLAUDE.md

Claude Desktop rejects `mcp-add`: add it under Settings > Connectors instead. Codex reads `~/.codex/config.toml` (TOML, server name `mem0`). The first tool call opens a browser sign-in, or send your A

Python reads `MEM0_API_KEY` if no key is passed. TypeScript does not read the environment: pass `apiKey: process.env.MEM0_API_KEY` yourself.

Gates applied: no_behavioural_pass.

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

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