skills/mem0/README.md
Add persistent memory to any AI application in minutes using Mem0 Platform or the open-source self-hosted SDK.
Part of the Mem0 Skill Graph: See also mem0-cli (terminal) and mem0-vercel-ai-sdk (Vercel AI SDK).
When installed, Claude can:
npx skills add https://github.com/mem0ai/mem0 --skill mem0
skills/mem0 folder as a ZIPcurl -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"}'
A Mem0 Platform API key (Get one here)
Python 3.10+ or Node.js 18+
Set the environment variable:
export MEM0_API_KEY="m0-your-api-key"
After installing, just ask Claude:
skills/mem0/
├── SKILL.md # Skill definition and instructions
├── README.md # This file
├── LICENSE # Apache-2.0
├── client/ # Language-specific SDK references (Platform + OSS)
│ ├── python.md # Python SDK (MemoryClient + Memory OSS)
│ ├── node.md # TypeScript SDK (MemoryClient + Memory OSS)
│ └── differences.md # Python vs TypeScript comparison
├── scripts/
│ └── mem0_doc_search.py # Search live Mem0 docs on demand
└── references/ # Documentation (loaded on demand)
├── quickstart.md # Full quickstart (Python, TS, cURL)
├── sdk-guide.md # All SDK methods (Python + TypeScript)
├── api-reference.md # REST endpoints, filters, memory object
├── architecture.md # Processing pipeline, lifecycle, scoping, performance
├── features.md # Retrieval, graph, categories, MCP, webhooks, multimodal
├── integration-patterns.md # LangChain, CrewAI, OpenAI Agents, LangGraph, LlamaIndex, etc.
└── use-cases.md # 7 real-world patterns with Python + TypeScript code
Apache-2.0