Catalog Systems Dedicated memory layers Mem0

Mem0

https://mem0.ai/

Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.

Active · Verified 2026-10-23 · fresh as of 2026-10-23 · 82 cited facts, 8 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Type
Vector + graph + KV (hybrid) vendor fix
Tier
T1
Section
Dedicated memory layers
Created
2023-06 vendor fix
Latest release
v2.2.1 (2026-09-25) — mem0ai on PyPI registry fix
License
Apache-2.0 repo fix
GitHub
mem0ai/mem0 — ~67.3k stars, last commit 2026-09+ repo fix
Pricing
Free + paid vendor fix
Funding
$24M total $150M val Series A · 2025-10 third-party fix
Freshness
2026-10-23 fix
Layer
agent-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
Accelerator
yc-s24 third-party fix
SDK languages
python, rest, typescript vendor fix
Protocols
mcp-server vendor fix
Compliance
gdpr, hipaa, soc2-type1 vendor fix
Developer activity
OpenRank 25.56 (12-mo avg 24.36) · 193 participants — 2026-09 third-party fix
Maintainer health
34 issues in 90 days, 76% answered or closed · 100 releases in 12 months (latest 2026-09-25) · bus factor 5 — as of 2026-11-01 repo

Memory taxonomy

storage
vector
retrieval
similarity
persistence
long-term
update
extraction
unit
fact
governance
opaque
conflict
llm-arbitrate

When to use

Optimised for: developer experience + universal memory layer (model-agnostic, multi-store)

Anti-fit: no anti-fit explicitly stated

Pros & cons

Pros

Hybrid (vector + graph + KV) gives the most architectural flexibility of any memory layer.

Cons

LOCOMO benchmark numbers were publicly disputed by Zep in counter-analysis; LLM-extraction approach risks dropping facts that don't fit the prompt.

Claims & capabilities

$24M Series A (Oct 2025) at $150M. Integrated memory provider for AWS's Strands Agents SDK (AWS partnership, 2025-05; not exclusive: AWS also offers AgentCore Memory for Strands). Reports 26% improvement over OpenAI on LOCOMO; 91% lower p95 latency vs full-context.

Technical surface

API surface
REST, SDK: Python, Node.js
Backend storage
hybrid (vector + graph + KV)
Deployment
Both
Embedding model
multiple supported
Multi-tenancy
Logical namespace per (user_id, agent_id, run_id); self-hosted/on-prem deployment available for tenant isolation
MCP
yes — official hosted Mem0 MCP server (docs.mem0.ai/platform/mem0-mcp); the self-hosted mem0-mcp repo was archived 2026-03-24
A2A
not documented publicly
OpenTelemetry
via adapter — AgentOps integration

Compare Mem0 with…

Alternatives to Mem0 → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other dedicated memory layers in the catalog, ranked by inbound references.

  • Zep & Graphiti T1

    Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.

  • Cognee T1

    "Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.

  • Hindsight (Vectorize) T1

    Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.

  • Letta / MemGPT T1

    Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompts over time.

  • Memori T2

    Structured, persistent memory layer for AI agents. Open source.

  • Memvid T2

    Single-file memory layer (one .mv2 file). No DB, no server. Append-only sequence of immutable Smart Frames with timestamps + checksums. Native Rust core (rewritten from Python).

Sources (81 cited facts, 8 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-22
    • Latest release “openclaw-v1.0.11 2026-04-29” → “v2.2.1 (2026-09-25) — mem0ai on PyPI” source
    • MCP support “native (first-party) — official mem0-mcp server” → “yes — official hosted Mem0 MCP server (docs.mem0.ai/platform/mem0-mcp); the self-hosted mem0-mcp repo was archived 2026-03-24” source
    #195

Related systems

References (49)

  • AgentOps integrates with — Mem0 docs have an AgentOps integration page (Integrate Mem0 with AgentOps for automatic monitoring, analytics, and real-time tracking of memory operations). (verified 2026-10-29)
  • Amazon Neptune Analytics builds on · integrates with — AWS architecture: build persistent memory with Mem0 open source, Amazon ElastiCache for Valkey and Amazon Neptune Analytics
  • Anthropic Claude (foundation models) integrates with — Mem0 docs have an Anthropic LLM provider page for Mem0 open source. (verified 2026-10-29)
  • AutoGen / AG2 integrates with — Mem0 docs have an AutoGen integration page (Build conversational AI agents with AutoGen and Mem0 for context-aware, personalized interactions). (verified 2026-10-29)
  • CAMEL integrates with — Mem0 docs have a Camel AI integration page (Plug Mem0 cloud memory into Camel's agents with the built‑in Mem0Storage). (verified 2026-10-29)
  • Chroma integrates with — Mem0 docs have a Chroma vector store page for Mem0 open source. (verified 2026-10-29)
  • Claude Code (Anthropic) integrates with — Mem0 docs have a Claude Code integration page (Persistent cross-session memory for Claude Code. Install once, memories are captured automatically and recalled in every future session). (verified 2026-10-29)
  • CrewAI integrates with — Mem0 docs have a CrewAI integration page (Combine CrewAI agent-based architecture with Mem0 for persistent memory across agent interactions). (verified 2026-10-29)
  • Cursor (IDE) integrates with — Mem0 docs have a Cursor integration page (Add persistent memory to Cursor with automatic capture, explicit recall, a search tool, and six memory skills). (verified 2026-10-29)
  • Databricks Vector Search (now Databricks AI Search) integrates with — Mem0 docs have a Databricks vector store page for Mem0 open source. (verified 2026-10-29)
  • DeepSeek R1 / V3 family integrates with — Mem0 docs have a DeepSeek LLM provider page for Mem0 open source. (verified 2026-10-29)
  • Dify integrates with — Mem0 docs have a Dify integration page (Integrate Mem0 as a plugin in Dify AI workflows for persistent conversation storage and retrieval). (verified 2026-10-29)
  • Elasticsearch integrates with — Mem0 docs have an Elasticsearch vector store page for Mem0 open source. (verified 2026-10-29)
  • ElevenLabs Conversational AI (now ElevenAgents) integrates with — Mem0 docs have an ElevenLabs integration page (Create voice-based conversational AI agents with ElevenLabs and Mem0 for context-aware voice interactions). (verified 2026-10-29)
  • Google Agent Development Kit (ADK) integrates with — Mem0 docs have a Google ADK integration page (Integrate Mem0 with Google Agent Development Kit for persistent memory across multi-agent workflows). (verified 2026-10-29)
  • Google Gemini 3 family integrates with — Mem0 docs have a Google AI as LLM Provider LLM provider page for Mem0 open source. (verified 2026-10-29)
  • Hermes Agent memory (Nous Research) integrates with — Mem0 docs have a Hermes Agent integration page (Add persistent memory to Hermes Agent with Mem0 Cloud, a self-hosted server, or the in-process OSS SDK). (verified 2026-10-29)
  • LangChain (framework) integrates with — Mem0 docs have a LangChain Integration integration page (Build personalized AI agents using LangChain for conversation flow and Mem0 for long-term memory retention). (verified 2026-10-29)
  • LangGraph (orchestration) integrates with — Mem0 docs have a LangGraph integration page (Build customer support agents using LangGraph for conversation flow and Mem0 for personalized responses). (verified 2026-10-29)
  • LiteLLM integrates with — Mem0 docs have a LiteLLM LLM provider page for Mem0 open source. (verified 2026-10-29)
  • LiveKit Agents integrates with — Mem0 docs have a Livekit integration page (Build memory-enabled voice assistants with LiveKit, Deepgram, OpenAI, and Mem0 for context-aware conversations). (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — Mem0 docs have a LlamaIndex integration page (Use Mem0 as a memory store in LlamaIndex with support for ReAct and FunctionCalling agent types). (verified 2026-10-29)
  • Mastra integrates with — Mem0 docs have a Mastra integration page (Use Mastra agents with Mem0 as the memory backend for cross-conversation storage and retrieval). (verified 2026-10-29)
  • Milvus integrates with — Mem0 docs have a Milvus vector store page for Mem0 open source. (verified 2026-10-29)
  • Mistral Large 2 / Mixtral family integrates with — Mem0 docs have a Mistral AI LLM provider page for Mem0 open source. (verified 2026-10-29)
  • MongoDB Atlas Vector Search integrates with — Mem0 docs have a MongoDB vector store page for Mem0 open source. (verified 2026-10-29)
  • n8n (AI agent flows) integrates with — Mem0 docs have a n8n Integration integration page (Add long-term memory to n8n workflows and AI Agents with the Mem0 community node, no code required). (verified 2026-10-29)
  • Neo4j depends on at runtime — adjacent-infrastructure cell: BYO LLM provider; bundles vector store (Qdrant default) and graph store (Neo4j optional)
  • OpenAI Agents SDK integrates with — Mem0 docs have an OpenAI Agents SDK integration page (Integrate Mem0 with the OpenAI Agents SDK for persistent memory across multi-agent workflows). (verified 2026-10-29)
  • OpenAI Codex CLI integrates with — Mem0 docs have a Codex integration page (Add persistent memory to OpenAI Codex with automatic capture, automatic recall, a search tool, and six memory skills). (verified 2026-10-29)
  • OpenAI Embeddings integrates with — Mem0 docs have an OpenAI embedder page for Mem0 open source. (verified 2026-10-29)
  • OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with — Mem0 docs have an OpenAI as LLM Provider LLM provider page for Mem0 open source. (verified 2026-10-29)
  • OpenClaw memory integrates with — Mem0 docs have an OpenClaw integration page (Add long-term memory to OpenClaw agents using the Mem0 plugin with skills-based memory extraction and recall). (verified 2026-10-29)
  • Opencode (SST) integrates with — Mem0 docs have an OpenCode integration page (Add persistent memory to OpenCode with the Mem0 plugin: native SDK-backed memory tools, lifecycle hooks, and skills). (verified 2026-10-29)
  • OpenSearch integrates with — Mem0 docs have an OpenSearch vector store page for Mem0 open source. (verified 2026-10-29)
  • pgvector integrates with — Mem0 docs have a pgvector vector store page for Mem0 open source. (verified 2026-10-29)
  • Phidata (now Agno) integrates with — Mem0 docs have an Agno integration page (Add persistent multimodal memory to Agno-based agents using Mem0 for text and image interactions). (verified 2026-10-29)
  • Pinecone integrates with — Mem0 docs have a Pinecone vector store page for Mem0 open source. (verified 2026-10-29)
  • Pipecat (Daily) integrates with — Mem0 docs have a Pipecat integration page (Integrate Mem0 with Pipecat for conversational memory in AI agents). (verified 2026-10-29)
  • Qdrant integrates with · depends on at runtime — adjacent-infrastructure cell: BYO LLM provider; bundles vector store (Qdrant default) and graph store (Neo4j optional)
  • Sentence Transformers integrates with — Mem0 docs have a Sentence Transformer reranker page. (verified 2026-10-29)
  • Strands Agents (AWS) integrates with — Mem0 docs have a Strands Agents integration page (Add persistent long-term memory to AWS Strands agents with Mem0, as a native MemoryStore that plugs into the agent loop). (verified 2026-10-29)
  • Supabase Vector integrates with — Mem0 docs have a Supabase vector store page for Mem0 open source. (verified 2026-10-29)
  • Together AI integrates with — Mem0 docs have a Together AI as LLM Provider LLM provider page for Mem0 open source. (verified 2026-10-29)
  • Turbopuffer integrates with — Mem0 docs have a Turbopuffer vector store page for Mem0 open source. (verified 2026-10-29)
  • Vercel AI SDK integrates with — Mem0 docs have a Vercel AI SDK integration page (Use the Mem0 AI SDK Provider with Vercel AI SDK for persistent memory in conversational AI applications). (verified 2026-10-29)
  • vLLM integrates with — Mem0 docs have a vLLM LLM provider page for Mem0 open source. (verified 2026-10-29)
  • Weaviate integrates with — Mem0 docs have a Weaviate vector store page for Mem0 open source. (verified 2026-10-29)
  • xAI Grok 4 integrates with — Mem0 docs have an xAI Grok as LLM Provider LLM provider page for Mem0 open source. (verified 2026-10-29)

Referenced by (27)

  • AgentOps integrates with — When Mem0 is connected, gains Memory Operation Timeline, Search Analytics, Memory Growth tracking, Error Tracking per memory call.
  • Amazon Neptune Analytics integrates with · depends on at runtime — Vector index on graph nodes queryable via openCypher. Mem0 integration GA 2025
  • AutoGen Memory integrates with — ListMemory chronological context + teachable agents that vectorise corrections. Integrates with Mem0/Zep rather than building deep memory natively.
  • Bedrock AgentCore (AWS) depends on at runtime — adjacent-infrastructure cell: AWS Bedrock; Mem0 (as memory provider); Strands Agents
  • Chroma integrates with — Chroma's docs have a Mem0 integration page. (verified 2026-10-29)
  • CrewAI depends on at runtime — Memory available via Mem0 / Letta adapters (CrewAI Memory cross-listed).
  • CrewAI Enterprise (now CrewAI AMP) depends on at runtime — adjacent-infrastructure cell: OSS CrewAI (already in catalog); typically paired with Mem0 / Zep for memory + Langfuse / LangSmith for observability
  • CrewAI Memory integrates with · depends on at runtime — Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
  • DSPy History integrates with — Official Mem0+DSPy tutorial.
  • FalkorDB builds on · depends on at runtime — Native GraphRAG SDK. Graph-memory backend for Mem0
  • Haystack (framework) integrates with — Haystack integrations directory has a Mem0 integration page ("Add persistent, user-specific memory to your Haystack agents and pipelines with Mem0"). (verified 2026-10-29)
  • Haystack Memory (deepset) integrates with — 18k+ stars; production via deepset Cloud; integrates Mem0 as a memory store alternative.
  • Inngest integrates with — Inngest AgentKit docs: AgentKit Memory concept page: long-term memory by integrating Mem0. (verified 2026-10-29)
  • Langflow integrates with — Langflow components bundle: Mem0 chat memory component. (verified 2026-10-29)
  • Langflow Memory integrates with — Bundled Mem0 + Redis integrations for external memory layers.
  • LlamaIndex (framework) integrates with — LlamaIndex has an official memory integration package llama-index-memory-mem0 in its repo. (verified 2026-10-29)
  • Mem0 MCP (official) builds on — Mem0's managed cloud API exposed as MCP tools.
  • Milvus integrates with — Milvus's integrations overview lists a Milvus + Mem0 integration tutorial. (verified 2026-10-29)
  • MongoDB Atlas Vector Search integrates with — MongoDB's Atlas AI Integrations page lists Mem0 as an integration (some entries are marked community-maintained). (verified 2026-10-29)
  • OpenMemory MCP builds on — Local-first self-hosted Mem0 variant. Shared memory layer bridges Claude Desktop, Cursor, and Windsurf in one session.
  • Phidata (now Agno) integrates with — Agno ships a mem0 toolkit (agno.tools.mem0). (verified 2026-10-29)
  • Pipecat (Daily) integrates with — Pipecat docs have a Mem0 service page. (verified 2026-10-29)
  • Qdrant integrates with — Qdrant's documentation has a Mem0 integration page. (verified 2026-10-29)
  • Ratine integrates with — Free / open source. Auto-detects Mem0 local, AutoGen, custom layouts.
  • Strands Agents Memory (AWS) integrates with · depends on at runtime — Memory via Mem0 integration (ElastiCache for Valkey + Neptune Analytics) or Bedrock AgentCore Memory. AWS+Mem0 partnership.
  • Vercel AI SDK integrates with — AI SDK docs have a Mem0 community provider page. (verified 2026-10-29)
  • Weaviate integrates with — Weaviate's integrations / model-provider docs list Mem0 as an integration. (verified 2026-10-29)