Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience real numbers from our own analytics — open to see them
–Visitors
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · counted by iTechGuides's own first-party analytics, bots removed, every figure rounded down · how we count

MrMemory review

#24 of 34 in AI Agent Memory Tools

Affordable managed memory with semantic search, agent sharing and self-hosting.

5.8/10Editor score
MrMemory5.8 Visit MrMemory

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

MrMemory is a hosted and self-hostable memory layer for developers building persistent, multi-session or multi-agent AI applications. Its REST and WebSocket APIs store memories with automatic embeddings, retrieve them through cosine-similarity search, and extract information from conversations. Python and TypeScript packages, HTTP access, configurable expiration and memory self-editing support teams that need an application-level memory service rather than a standalone chat interface.

Pricing is straightforward for small deployments. The Starter plan costs $5 per month and includes 10,000 memories, 50,000 API calls per month, five agents, semantic vector search, auto-embedding and memory compression. A 7-day free trial is available for hosted Starter. Pro costs $25 per month and raises capacity to 100,000 memories and 500,000 API calls per month, while adding unlimited agents, WebSocket real-time sync, memory governance and priority support. There is no free plan, so teams evaluating beyond the trial need a paid subscription.

Its ecosystem fit is a central strength: integrations cover LangChain, LangGraph, CrewAI, AutoGen and OpenClaw, with LangChain/LangGraph checkpointer and store support. Three-layer governance, configurable retention, LLM summarization, merging and pruning give builders control over how memories evolve. Docker Compose self-hosting suits teams that need deployment control, while hosted access reduces infrastructure work. MrMemory fits small and mid-market teams that want managed memory with an option to self-host; teams requiring a free tier, broad support channels or a more established release should consider other tools.

MrMemory pros and cons

  • Where it wins
    • Semantic search with automatic embedding and conversation extraction
    • Multi-agent sharing, compression, self-editing and governance
    • Cloud API plus Docker Compose self-hosting and framework integrations
  • Where it doesn't
    • No free plan; access starts at $5 per month
    • Starter limits usage to 10,000 memories, 50,000 API calls and 5 agents
    • Support is documentation-based, and the product is labeled Early Access

MrMemory fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. How we rank.

Last updated · How we research and update