Skip to content

Memory, kept. See and edit what your agents remember.

Hosted memory for AI agents

Connect Claude, Cursor, or Claude Code over MCP and watch, search, and correct what they remember — not a black-box memory API.

Works with Claude Desktop, Cursor, and Claude Code

No credit card required · Bring your own OpenAI key

Built for the MCP-native agent ecosystem.

The problem

Your agents are building memory you can't see.

Self-hosting agentwiki means one SQLite file per laptop — no sharing, no roles. Hosted memory APIs hide everything behind an endpoint. Either way, when an agent remembers something wrong, you can't open it up and fix it.

Connect

Connect in two lines.

One remote MCP URL and one org API key. Paste them into Claude, Cursor, or Claude Code — the agent connects and your memory starts to appear. No SDK, no server, no infrastructure to provision.

connect — remote MCP

live

Same endpoint, same per-org key — pick your client:

{
  "mcpServers": {
    "stored": {
      "url": "https://mcp.stored.to/v1/sse",
      "headers": {
        "Authorization": "Bearer mm_live_your_org_key"
      }
    }
  }
}
  1. 1

    Paste URL + key

    Drop the remote MCP endpoint and your org API key into your client.

  2. 2

    Agent connects

    Your client opens the remote MCP session over SSE — no server to run.

  3. 3

    Memory appears

    As your agent saves memories they show up live in your workspace.

Live memory graph

Watch your agents remember, in real time.

Every memory your agents write lands in a live graph of entities and relationships. The invisible process of an agent building context becomes something your whole team can see.

  • Nodes and edges update as memories are saved
  • Browse by entity, source, or recency
  • The “watch your AI remember” moment, hosted
Live
Visible & editable

When an agent gets it wrong, you fix it.

Every memory carries provenance — which agent or source wrote it, and when. If it is outdated or wrong, you correct it or delete it. The memory is yours to govern, not the model’s to guess.

  • Provenance on every memory
  • Edit or delete what an agent got wrong
  • Full history, not an opaque endpoint

provenance & history

  • claude-desktopwrote “uses Postgres 16”· 2h ago
  • cursorconfirmed via repo scan· yesterday
  • claude-codecreated entity Acme· last week
Edit memoryDelete

Correct the model when it drifts — every change is logged and shared across your team’s connected agents.

Pricing

Start free, scale when you need to.

Free to try, Pro for growing teams, Team for whole organizations, and Enterprise for custom needs.

Solo

For solo builders

$0forever

 

Connect an agent and watch your memory grow — generous and free.

  • 10,000 stored memories
  • 100,000 agent calls / month
  • Up to 3 members
  • Remote MCP endpoint + org API key
Most popular

Builder

For serious builders

$19/ mo

or $190 billed yearly

Room to grow, premium retrieval, and unlimited teammates.

  • 250,000 stored memories
  • 2,000,000 agent calls / month
  • Unlimited members — humans are free
  • Premium reranker for sharper retrieval

Scale

For scaling agent fleets

$99/ mo

or $990 billed yearly

Usage-based for heavy agent traffic. You pay for memory and calls — never for people.

  • 1,000,000 memories included, then metered
  • 20,000,000 agent calls included, then metered
  • Usage: $5 / 100k memories · $2 / 1M calls
  • Unlimited members — humans are free

Enterprise

For larger orgs

Customcontact us

 

Dedicated or self-hosted data plane, SSO, and security review.

  • Dedicated or self-hosted data plane
  • SSO + custom contracts and SLAs
  • Volume usage commitments + discounts
  • Priority support and security review
FAQ

Questions, answered.

mem0's hosted store is a black box — you cannot see or correct what your agents remember. stored makes every memory visible, sourced, and editable from a dashboard, on top of the open-source agentwiki engine.

A few minutes. You create an organization, copy your remote MCP URL and an org API key, and paste them into your agent's config. No infrastructure to provision.

Any MCP-capable client. We test against Claude Desktop, Cursor, and Claude Code, all over the same remote MCP endpoint with a per-org API key.

No. The Free plan needs no card. You can connect an agent, watch your first memories appear, and upgrade later from inside the app.

Memory is stored in the agentwiki engine and surfaced in your dashboard. Every memory shows which agent wrote it and when, and you can correct or delete anything an agent got wrong.

You bring your own OpenAI key per organization, and it is encrypted at rest. It powers embeddings and extraction for your workspace only.

See what your agents remember.

Hosted, visible, editable memory for AI agents — built on the open engine. Connect an agent and watch your first memory appear.

No credit card required · Bring your own OpenAI key

SEE WHAT YOUR AGENTS REMEMBER