stored — 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.

Memory you can see

Start free Talk to sales

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.

How it works

Paste a URL and a key. Your agents remember.

No SDK, no server, no infrastructure to provision. Connect over the remote MCP endpoint and reach your first memory in minutes.

Create your workspace

Connect an agent

Paste the remote MCP URL and an org API key into Claude, Cursor, or Claude Code.

Watch the memory build

As your agents save memories they appear live — searchable, sourced, and yours to edit.

remote MCP · one endpoint

live

Claude DesktopCursorClaude Code

remote MCP endpointmcp.stored.ioshared memoryone graph, per-org key

2 · connect an agent

remote MCP

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

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

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.io/v1/sse",
      "headers": {
        "Authorization": "Bearer mm_live_your_org_key"
      }
    }
  }
}

1
Paste URL + key
Drop the remote MCP endpoint and your org API key into your client.
2
Agent connects
Your client opens the remote MCP session over SSE — no server to run.
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

PostgresVercelacme-apipnpm/v2 API

Live

Hybrid retrieval

Graph, vector, and wiki signals in one search.

A single query pulls structured links, semantic matches, and wiki context together — then reranks them. The exact engine behind open-source agentwiki, with a premium reranker on paid plans.

search · hybrid retrieval

what database do we use?

graphacme-api → Postgres + pgvectorvectorMigrated off SQLite in MarchwikiInfra page: connection pooling

merge + rerankranked #1acme-api → Postgres + pgvector

0signals merged

Graph, vector, and wiki signals, merged — with a premium reranker on paid plans.

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.

Multiplayer memory

You and your agents, editing one memory

Think of it like a shared canvas: you and every connected agent work the same memory. What one writes, the next can read — no copy stuck on a laptop.

Synced

One shared memory

memory

editingYou&Claude

An illustration of the idea — agents read and write over MCP against one shared graph, not literal live cursors.

Team workspace

One shared memory, with roles and keys.

Invite your team into an organization with owner, admin, and member roles. Everyone connects to the same shared memory and sees the same graph — instead of a SQLite file stuck on one machine.

Owner

Full control — billing, members, and keys.

Admin

Manage members, agents, and memory.

Member

Connect agents and work the shared graph.

One shared memory

Every role, every agent, the same graph — governed in one place.

mm_live_ac…7f2mm_live_ci…9b4

per-org API keys

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

Start free

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

Start building

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

Start scaling

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

Talk to sales

See full pricing details →

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.

Start free Talk to sales

No credit card required · Bring your own OpenAI key

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

Your agents are building memory you can't see.

Paste a URL and a key. Your agents remember.

Create your workspace

Connect an agent

Watch the memory build

Connect in two lines.

Paste URL + key

Agent connects

Memory appears

Watch your agents remember, in real time.

Graph, vector, and wiki signals in one search.

When an agent gets it wrong, you fix it.

You and your agents, editing one memory

memory

One shared memory, with roles and keys.

Start free, scale when you need to.

Solo

Builder

Scale

Enterprise

Questions, answered.

How is this different from mem0?

How long does setup take?

Which agents and tools does it work with?

Do I need a credit card to start?

Where does the memory live, and can I edit it?

Do you store my OpenAI key?

See what your agents remember.