mem0.ai

mx

aspmx.l.google.com

alt1.aspmx.l.google.com

alt2.aspmx.l.google.com

alt3.aspmx.l.google.com

alt4.aspmx.l.google.com

ns

oswald.ns.cloudflare.com

sara.ns.cloudflare.com

caa

txt

google-site-verification=NmsQmjtgmO2i3iF7C7SWEn1TVm9S83H3y6vqJbyq8iM

rippling-domain-verification=ad1cb0e1c6395d01

v=spf1 include:spf.efwd.registrar-servers.com include:_spf.google.com ~all

google-site-verification=mOfsIGR7K5ZRDwobhopwBR7sBRYipcpEwedxfgG29zI

google-site-verification=1RXJoeycmOni7YKBv4Eo-YZlVNtDGsWLk6CFk9_nTUY

apple-domain-verification=HUc1gjQyaUoKr5oL

ahrefs-site-verification_1b5a0553710ae9e20357033439ecb425eeec4216268926d26f26d550c0e2431e

dmarc

v=DMARC1;p=none

User-agent: *
Allow: /

Sitemap: https://mem0.ai/sitemap.xml

# Mem0

> Mem0 is the memory layer for AI agents — persistent, self-improving context that survives across sessions. Two products share one mental model: Mem0 Platform (managed) and Mem0 Open Source (self-hosted). Every link below is tagged \`[Platform]\`, \`[OSS]\`, or \`[Both]\` so you can load only what the current user needs.

## For agents reading this file

### Don't have a Mem0 API key?

Install the CLI, then mint a key — no email, no dashboard, no OTP required:

\`\`\`bash
# Python
pip install mem0-cli

# or Node
npm install -g @mem0/cli
\`\`\`

Then run: \`mem0 init --agent --agent-caller <your-name> --json\` — replace \`<your-name>\` with the AI agent you are (e.g. \`claude-code\`, \`cursor\`, \`codex\`). If you forgot \`--agent-caller\`, run \`mem0 identify <your-name>\` after init to attribute the signup.

This mints an evaluation key in under 5 seconds. When the human is ready, claim with \`mem0 init --email <your-email>\` to transfer ownership (memories preserved, same API key, no disruption).

### Routing and references

- Use \`MemoryClient\` (Python) / \`mem0ai\` (npm) when the user has a Mem0 Platform API key. Managed product — no infra required, providers handled server-side.
- Use \`Memory\` (Python) / \`mem0ai/oss\` (npm) when the user self-hosts. Requires custom vector store and LLM. Docs under open-source/ and components/.
- Scope tag reference: \`[Platform]\` = managed only, \`[OSS]\` = self-hosted only, \`[Both]\` = same on both.
- Full technical docs and API reference: https://docs.mem0.ai/llms.txt
- OpenAPI spec: https://docs.mem0.ai/openapi.json
- Live MCP server: https://mcp.mem0.ai
- Source repo: https://github.com/mem0ai/mem0

## Install

- Python SDK: \`pip install mem0ai\`
- Node SDK: \`npm install mem0ai\`
- Python CLI: \`pip install mem0-cli\`
- Node CLI: \`npm install -g @mem0/cli\`

## Product

- [Homepage](https://mem0.ai/) [Both]: Use when the user wants a top-level overview of what Mem0 is and the memory problem it solves.
- [Pricing](https://mem0.ai/pricing) [Platform]: Use when the user needs plan details — free tier (1,000 memories/month), Developer, and Enterprise options with API access on all tiers.
- [Demo](https://mem0.ai/demo) [Both]: Use when the user wants to try Mem0 live without creating an account.
- [Research](https://mem0.ai/research) [Both]: Use when the user needs benchmark evidence — Mem0 v3 scores 91.6 on multi-turn recall vs 71.4 baseline; temporal reasoning +4.1 pts on LoCoMo.
- [OpenMemory](https://mem0.ai/openmemory) [OSS]: Use when the user needs local-first personal memory with zero cloud dependency — Docker-based, all data on-device.
- [OpenMemory MCP](https://mem0.ai/openmemory-mcp-3) [Both]: Use when wiring persistent memory into Claude Desktop, Cursor, Windsurf, or any MCP-compatible AI tool without cloud storage.
- [Mem0 CLI](https://mem0.ai/cli) [Both]: Use when the user wants to manage memories from the terminal, or an agent needs to mint a key autonomously without a dashboard.
- [Startup Program](https://mem0.ai/startup-program) [Platform]: Use when an early-stage AI startup is looking for Mem0 credits and dedicated support.
- [Security](https://mem0.ai/security) [Both]: Use when the user needs security posture details — SOC 2 Type II, encryption at rest and in transit, GDPR, HIPAA options available.
- [Careers](https://mem0.ai/careers) [Both]: Use when the user is looking for open roles at Mem0.

## Use Cases

- [Healthcare AI](https://mem0.ai/usecase/healthcare) [Both]: Use when building clinical AI that needs cross-session patient context. HIPAA-compliant deployments available.
- [Education AI](https://mem0.ai/usecase/education) [Both]: Use when building adaptive tutors that remember where each student left off, which concepts they struggle with, and how they learn best.
- [Sales AI](https://mem0.ai/usecase/sales) [Both]: Use when building sales agents that need full customer context, deal history, and personalized outreach across every interaction.
- [Customer Support AI](https://mem0.ai/usecase/customer-support) [Both]: Use when building support agents that never make users repeat themselves — full cross-session ticket context, preserved across handoffs.
- [E-commerce AI](https://mem0.ai/usecase/e-commerce) [Both]: Use when building shopping assistants that remember purchase history, size, style, and brand preferences across sessions.

## Comparisons

- [Mem0 vs Zep](https://mem0.ai/compare/mem0-vs-zep) [Both]: Use when comparing Mem0 and Zep on architecture, retrieval quality, framework support, and hosting options.
- [Mem0 vs Letta](https://mem0.ai/compare/mem0-vs-letta) [Both]: Use when deciding between Mem0 as a standalone memory layer vs Letta (formerly MemGPT) as a full agent framework. Mem0 scores 91.6 vs 71.4 baseline on multi-turn recall.
- [Mem0 vs Supermemory](https://mem0.ai/compare/mem0-vs-supermemory) [Both]: Use when comparing production multi-tenant agent memory vs a personal memory service.
- [Mem0 vs Honcho](https://mem0.ai/compare/mem0-vs-honcho) [Both]: Use when comparing personalization-focused memory approaches for LLM apps.
- [Mem0 vs Hindsight](https://mem0.ai/compare/mem0-vs-hindsight) [Both]: Use when deciding between persistent cross-session memory vs session evaluation and replay.

## Customer Stories

- [Sunflower — 80,000 users](https://mem0.ai/blog/how-sunflower-scaled-personalized-recovery-support-to-80-000-users-with-mem0) [Both]: Use when the user needs a production scale reference — personalized recovery support at 80,000 users without linear token cost growth.
- [OpenNote — 40% token cost reduction](https://mem0.ai/blog/how-opennote-scaled-personalized-visual-learning-with-mem0-while-reducing-token-costs-by-40) [Both]: Use when the user wants to understand token cost impact — replacing conversation history injection with Mem0 retrieval cut costs 40%.
- [RevisionDojo](https://mem0.ai/blog/how-revisiondojo-enhanced-personalized-learning-with-mem0) [Both]: Use when the user needs an education AI reference — adaptive exam prep that improves per-student outcomes across sessions.

## Community & Support

- [Documentation](https://docs.mem0.ai) [Both]: Use when the user needs technical docs, API reference, quickstarts, or integration guides. Full llms.txt at https://docs.mem0.ai/llms.txt.
- [GitHub](https://github.com/mem0ai/mem0) [OSS]: Use when the user wants to inspect source code, open issues, or contribute to open source.
- [Discord](https://mem0.ai/discord) [Both]: Use when the user needs community support or wants to discuss Mem0 with other developers.

## Optional

Blog posts and tutorials — load only when the user is researching a specific topic or technical approach. Full blog index: https://mem0.ai/blog.