Skip to content
Back to search

mem0-plugins

MarketplaceWorks with Claude CodeGitHub

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/mem0ai/mem0 with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/mem0ai/mem0'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/mem0ai-mem0/badge.svg)](/listings/mem0ai-mem0)

HTML

<a href="/listings/mem0ai-mem0"><img src="/api/listings/mem0ai-mem0/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Sign up as an agent

AI agents can mint a working Mem0 API key in under five seconds — no email, no dashboard, no OTP. Four commands end-to-end:

# 1. Install
npm install -g @mem0/cli      # or: pip install mem0-cli

# 2. Sign up as an agent (replace `claude-code` with your name)
mem0 init --agent --agent-caller claude-code

# 3. Add a memory
mem0 add "I am using mem0"

# 4. Search
mem0 search "am I using mem0"

The human owner can claim the account later with `mem0 init --email <their-email>` — same key, memories preserved. Full guide: [Sign up as an agent](https://docs.mem0.ai/platform/agent-signup).

| | Library | Self-Hosted Server | Cloud Platform | |---|---------|-------------------|----------------| | **Best for** | Testing, prototyping | Teams running on their own infrastructure | Zero-ops production use | | **Setup** | `pip install mem0ai` | `docker compose up` | Sign up at [app.mem0.ai](https://app.mem0.ai?utm_source=oss&utm_medium=readme) | | **Dashboard** | -- | [Yes](https://docs.mem0.ai/open-source/setup) | Yes | | **Auth & API Keys** | -- | Yes | Yes | | **Advanced Features** | -- | Teasers | All included |

Just testing? Use the library. Building for a team? Self-hosted. Want zero ops? Cloud.

Library (pip / npm)

pip install mem0ai

For enhanced hybrid search with BM25 keyword matching and entity extraction, install with NLP support:

pip install mem0ai[nlp]
python -m spacy download en_core_web_sm

Install sdk via npm:

npm install mem0ai

Self-Hosted Server

> **Note:** Self-hosted auth is on by default. Upgrading from a pre-auth build? Set `ADMIN_API_KEY`, register an admin through the wizard, or `AUTH_DISABLED=true` for local dev only. See [upgrade notes](https://docs.mem0.ai/open-source/setup#upgrade-notes).

# Recommended: one command — start the stack, create an admin, issue the first API key.
cd server && make bootstrap

# Manual: start the stack and finish setup via the browser wizard.
cd server && docker compose up -d    # http://localhost:3000

See the [self-hosted docs](https://docs.mem0.ai/open-source/overview) for configuration.

Cloud Platform

1. Sign up on [Mem0 Platform](https://app.mem0.ai?utm_source=oss&utm_medium=readme) 2. Embed the memory layer via SDK or API keys 3. Using hosted Qdrant vectors? See the [Platform migration guide](https://docs.mem0.ai/migration/oss-to-platform) to import them into Mem0 Platform.

CLI

Manage memories from your terminal:

npm install -g @mem0/cli   # or: pip install mem0-cli

mem0 init
mem0 add "Prefers dark mode and vim keybindings" --user-id alice
mem0 search "What does Alice prefer?" --user-id alice

See the [CLI documentation](https://docs.mem0.ai/platform/cli) for the full command reference.

Agent Skills

Teach your AI coding assistant (Claude Code, Codex, Cursor, Windsurf, OpenCode, OpenClaw, and any tool that supports the skills standard) how to build with Mem0. Two categories:

**Reference skills — always on** (SDK knowledge loaded into the assistant's context):

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

**Pipeline skills — run on demand** (execute an end-to-end workflow in an existing repo):

npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate
npx skills add https://github.com/mem0ai/mem0 --skill mem0-test-integration
npx skills add https://github.com/mem0ai/mem0 --skill mem0-oss-to-platform

Use `/mem0-integrate` to wire Mem0 into an existing repo via a test-first pipeline, then `/mem0-test-integration` to verify. Use `/mem0-oss-to-platform` to migrate an existing project from Mem0 OSS to the hosted Platform SDK. See the [skills catalog](./skills/) or [Vibecoding with Mem0](https://docs.mem0.ai/vibecoding) for the full picture.

Basic Usage

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 18 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "mem0-plugins",
  3. "owner": {
  4. "name": "Mem0",
  5. "email": "support@mem0.ai"
  6. },
  7. "metadata": {
  8. "description": "Official Mem0 plugins for Claude"
  9. },
  10. "plugins": [
  11. {
  12. "name": "mem0",
  13. "source": "./integrations/claude-code-plugin",
  14. "description": "Cross-session memory and token savings for coding agents.",
  15. "version": "0.3.3"
  16. }
  17. ]
  18. }
README.md · README · 280 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <a href="https://github.com/mem0ai/mem0">
  3. <img src="docs/images/banner-sm.png" width="800px" alt="Mem0 - The Memory Layer for Personalized AI">
  4. </a>
  5. </p>
  6. <p align="center">
  7. <a href="https://luma.com/mem0-oxfm">
  8. <img src="docs/images/halloween-happy-hour.png" width="450px" alt="Mem0 OSS Halloween Happy Hour: The People Who Read the Source. Tuesday, Oct 27, 5:00 PM, San Francisco. Costumes encouraged.">
  9. </a>
  10. <br>
  11. <a href="https://luma.com/mem0-oxfm"><strong>🎃 Register here →</strong></a> · Contributors get priority
  12. </p>
  13. <p align="center" style="display: flex; justify-content: center; gap: 20px; align-items: center;">
  14. <a href="https://trendshift.io/repositories/11194" target="blank">
  15. <img src="https://trendshift.io/api/badge/repositories/11194" alt="mem0ai%2Fmem0 | Trendshift" width="250" height="55"/>
  16. </a>
  17. </p>
  18. <p align="center">
  19. <a href="https://mem0.ai">Learn more</a>
  20. ·
  21. <a href="https://mem0.dev/DiG">Join Discord</a>
  22. ·
  23. <a href="https://mem0.dev/demo">Demo</a>
  24. </p>
  25. <p align="center">
  26. <a href="https://mem0.dev/DiG">
  27. <img src="https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white" alt="Mem0 Discord">
  28. </a>
  29. <a href="https://pepy.tech/project/mem0ai">
  30. <img src="https://img.shields.io/pypi/dm/mem0ai" alt="Mem0 PyPI - Downloads">
  31. </a>
  32. <a href="https://github.com/mem0ai/mem0">
  33. <img src="https://img.shields.io/github/commit-activity/m/mem0ai/mem0?style=flat-square" alt="GitHub commit activity">
  34. </a>
  35. <a href="https://pypi.org/project/mem0ai" target="blank">
  36. <img src="https://img.shields.io/pypi/v/mem0ai?color=%2334D058&label=pypi%20package" alt="Package version">
  37. </a>
  38. <a href="https://www.npmjs.com/package/mem0ai" target="blank">
  39. <img src="https://img.shields.io/npm/v/mem0ai" alt="Npm package">
  40. </a>
  41. <a href="https://www.ycombinator.com/companies/mem0">
  42. <img src="https://img.shields.io/badge/Y%20Combinator-S24-orange?style=flat-square" alt="Y Combinator S24">
  43. </a>
  44. </p>
  45. <p align="center">
  46. <a href="https://mem0.ai/research"><strong>📄 Benchmarking Mem0's token-efficient memory algorithm →</strong></a>
  47. </p>
  48. ## New Memory Algorithm (April 2026)
  49. | Benchmark | Old | New | Tokens | Latency p50 |
  50. | --- | --- | --- | --- | --- |
  51. | **LoCoMo** | 71.4 | **92.5** | 7.0K | 0.88s |
  52. | **LongMemEval** | 67.8 | **94.4** | 6.8K | 1.09s |
  53. | **BEAM (1M)** | — | **64.1** | 6.7K | 1.00s |
  54. | **BEAM (10M)** | — | **48.6** | 6.9K | 1.05s |
  55. All benchmarks run on the same production-representative model stack. Single-pass retrieval (one call, no agentic loops) at a top_200 retrieval budget. Scores reflect Mem0's managed platform, which includes proprietary optimizations not available in the open-source SDK; open-source users should expect directionally similar gains but not identical numbers.
  56. **What changed:**
  57. - **Single-pass ADD-only extraction** -- one LLM call, no UPDATE/DELETE. Memories accumulate; nothing is overwritten.
  58. - **Agent-generated facts are first-class** -- when an agent confirms an action, that information is now stored with equal weight.
  59. - **Entity linking** -- entities are extracted, embedded, and linked across memories for retrieval boosting.
  60. - **Multi-signal retrieval** -- semantic, BM25 keyword, and entity matching scored in parallel and fused.
  61. - **Temporal Reasoning** -- time-aware retrieval that ranks the right dated instance for queries about current state, past events, and upcoming plans.
  62. See the [migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for upgrade instructions. The [evaluation framework](https://github.com/mem0ai/memory-benchmarks) is open-sourced so anyone can reproduce the numbers.
  63. ## Research Highlights
  64. - **92.5 on LoCoMo** -- +21 points over the previous algorithm
  65. - **94.4 on LongMemEval** -- +27 points, with 98.2 on assistant memory recall
  66. - **64.1 on BEAM (1M)** -- production-scale memory evaluation at 1M tokens
  67. - [Read the full paper](https://mem0.ai/research)
  68. # Introduction
  69. [Mem0](https://mem0.ai) ("mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. It remembers user preferences, adapts to individual needs, and continuously learns over time—ideal for customer support chatbots, AI assistants, and autonomous systems.
  70. ### Key Features & Use Cases
  71. **Core Capabilities:**
  72. - **Multi-Level Memory**: Seamlessly retains User, Session, and Agent state with adaptive personalization
  73. - **Developer-Friendly**: Intuitive API, cross-platform SDKs, and a fully managed service option
  74. **Applications:**
  75. - **AI Assistants**: Consistent, context-rich conversations
  76. - **Customer Support**: Recall past tickets and user history for tailored help
  77. - **Healthcare**: Track patient preferences and history for personalized care
  78. - **Productivity & Gaming**: Adaptive workflows and environments based on user behavior
  79. ## 🚀 Quickstart Guide <a name="quickstart"></a>
  80. ### Sign up as an agent
  81. AI agents can mint a working Mem0 API key in under five seconds — no email, no dashboard, no OTP. Four commands end-to-end:
  82. ```bash
  83. # 1. Install
  84. npm install -g @mem0/cli # or: pip install mem0-cli
  85. # 2. Sign up as an agent (replace `claude-code` with your name)
  86. mem0 init --agent --agent-caller claude-code
  87. # 3. Add a memory
  88. mem0 add "I am using mem0"
  89. # 4. Search
  90. mem0 search "am I using mem0"
  91. ```
  92. The human owner can claim the account later with `mem0 init --email <their-email>` — same key, memories preserved. Full guide: [Sign up as an agent](https://docs.mem0.ai/platform/agent-signup).
  93. | | Library | Self-Hosted Server | Cloud Platform |
  94. |---|---------|-------------------|----------------|
  95. | **Best for** | Testing, prototyping | Teams running on their own infrastructure | Zero-ops production use |
  96. | **Setup** | `pip install mem0ai` | `docker compose up` | Sign up at [app.mem0.ai](https://app.mem0.ai?utm_source=oss&utm_medium=readme) |
  97. | **Dashboard** | -- | [Yes](https://docs.mem0.ai/open-source/setup) | Yes |
  98. | **Auth & API Keys** | -- | Yes | Yes |
  99. | **Advanced Features** | -- | Teasers | All included |
  100. Just testing? Use the library. Building for a team? Self-hosted. Want zero ops? Cloud.
  101. ### Library (pip / npm)
  102. ```bash
  103. pip install mem0ai
  104. ```
  105. For enhanced hybrid search with BM25 keyword matching and entity extraction, install with NLP support:
  106. ```bash
  107. pip install mem0ai[nlp]
  108. python -m spacy download en_core_web_sm
  109. ```
  110. Install sdk via npm:
  111. ```bash
  112. npm install mem0ai
  113. ```
  114. ### Self-Hosted Server
  115. > **Note:** Self-hosted auth is on by default. Upgrading from a pre-auth build? Set `ADMIN_API_KEY`, register an admin through the wizard, or `AUTH_DISABLED=true` for local dev only. See [upgrade notes](https://docs.mem0.ai/open-source/setup#upgrade-notes).
  116. ```bash
  117. # Recommended: one command — start the stack, create an admin, issue the first API key.
  118. cd server && make bootstrap
  119. # Manual: start the stack and finish setup via the browser wizard.
  120. cd server && docker compose up -d # http://localhost:3000
  121. ```
  122. See the [self-hosted docs](https://docs.mem0.ai/open-source/overview) for configuration.
  123. ### Cloud Platform
  124. 1. Sign up on [Mem0 Platform](https://app.mem0.ai?utm_source=oss&utm_medium=readme)
  125. 2. Embed the memory layer via SDK or API keys
  126. 3. Using hosted Qdrant vectors? See the [Platform migration guide](https://docs.mem0.ai/migration/oss-to-platform) to import them into Mem0 Platform.
  127. ### CLI
  128. Manage memories from your terminal:
  129. ```bash
  130. npm install -g @mem0/cli # or: pip install mem0-cli
  131. mem0 init
  132. mem0 add "Prefers dark mode and vim keybindings" --user-id alice
  133. mem0 search "What does Alice prefer?" --user-id alice
  134. ```
  135. See the [CLI documentation](https://docs.mem0.ai/platform/cli) for the full command reference.
  136. ### Agent Skills
  137. Teach your AI coding assistant (Claude Code, Codex, Cursor, Windsurf, OpenCode, OpenClaw, and any tool that supports the skills standard) how to build with Mem0. Two categories:
  138. **Reference skills — always on** (SDK knowledge loaded into the assistant's context):
  139. ```bash
  140. npx skills add https://github.com/mem0ai/mem0 --skill mem0
  141. npx skills add https://github.com/mem0ai/mem0 --skill mem0-cli
  142. npx skills add https://github.com/mem0ai/mem0 --skill mem0-vercel-ai-sdk
  143. ```
  144. **Pipeline skills — run on demand** (execute an end-to-end workflow in an existing repo):
  145. ```bash
  146. npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate
  147. npx skills add https://github.com/mem0ai/mem0 --skill mem0-test-integration
  148. npx skills add https://github.com/mem0ai/mem0 --skill mem0-oss-to-platform
  149. ```
  150. Use `/mem0-integrate` to wire Mem0 into an existing repo via a test-first pipeline, then `/mem0-test-integration` to verify. Use `/mem0-oss-to-platform` to migrate an existing project from Mem0 OSS to the hosted Platform SDK. See the [skills catalog](./skills/) or [Vibecoding with Mem0](https://docs.mem0.ai/vibecoding) for the full picture.
  151. ### Basic Usage
  152. Mem0 requires an LLM to function, with `gpt-5-mini` from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to our [Supported LLMs documentation](https://docs.mem0.ai/components/llms/overview).
  153. Mem0 uses `text-embedding-3-small` from OpenAI as the default embedding model. For best results with hybrid search (semantic + keyword + entity boosting), we recommend using at least [Qwen 600M](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct) or a comparable embedding model. See [Supported Embeddings](https://docs.mem0.ai/components/embedders/overview) for configuration details.
  154. First step is to instantiate the memory:
  155. ```python
  156. from openai import OpenAI
  157. from mem0 import Memory
  158. openai_client = OpenAI()
  159. memory = Memory()
  160. def chat_with_memories(message: str, user_id: str = "default_user") -> str:
  161. # Retrieve relevant memories
  162. relevant_memories = memory.search(query=message, filters={"user_id": user_id}, top_k=3)
  163. memories_str = "\n".join(f"- {entry['memory']}" for entry in relevant_memories["results"])
  164. # Generate Assistant response
  165. system_prompt = f"You are a helpful AI. Answer the question based on query and memories.\nUser Memories:\n{memories_str}"
  166. messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": message}]
  167. response = openai_client.chat.completions.create(model="gpt-5-mini", messages=messages)
  168. assistant_response = response.choices[0].message.content
  169. # Create new memories from the conversation
  170. messages.append({"role": "assistant", "content": assistant_response})
  171. memory.add(messages, user_id=user_id)
  172. return assistant_response
  173. def main():
  174. print("Chat with AI (type 'exit' to quit)")
  175. while True:
  176. user_input = input("You: ").strip()
  177. if user_input.lower() == 'exit':
  178. print("Goodbye!")
  179. break
  180. print(f"AI: {chat_with_memories(user_input)}")
  181. if __name__ == "__main__":
  182. main()
  183. ```
  184. For detailed integration steps, see the [Quickstart](https://docs.mem0.ai/quickstart) and [API Reference](https://docs.mem0.ai/api-reference).
  185. ## 🔗 Integrations & Demos
  186. - **ChatGPT with Memory**: Personalized chat powered by Mem0 ([Live Demo](https://mem0.dev/demo))
  187. - **Browser Extension**: Store memories across ChatGPT, Perplexity, and Claude ([Chrome Extension](https://chromewebstore.google.com/detail/onihkkbipkfeijkadecaafbgagkhglop?utm_source=item-share-cb))
  188. - **Langgraph Support**: Build a customer bot with Langgraph + Mem0 ([Guide](https://docs.mem0.ai/integrations/langgraph))
  189. - **CrewAI Integration**: Tailor CrewAI outputs with Mem0 ([Example](https://docs.mem0.ai/integrations/crewai))
  190. ## 📚 Documentation & Support
  191. - Full docs: https://docs.mem0.ai
  192. - Community: [Discord](https://mem0.dev/DiG) · [X (formerly Twitter)](https://x.com/mem0ai)
  193. - Contact: founders@mem0.ai
  194. ## Citation
  195. We now have a paper you can cite:
  196. ```bibtex
  197. @article{mem0,
  198. title={Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory},
  199. author={Chhikara, Prateek and Khant, Dev and Aryan, Saket and Singh, Taranjeet and Yadav, Deshraj},
  200. journal={arXiv preprint arXiv:2504.19413},
  201. year={2025}
  202. }
  203. ```
  204. ## ⚖️ License
  205. Apache 2.0 — see the [LICENSE](https://github.com/mem0ai/mem0/blob/main/LICENSE) file for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.