Your AI finally
remembers everything.

Set up a private AI memory vault in about a minute. No migration, no setup call, no card required.

Claude opens with imem prefilled. Add the connector, click Connect, then sign in with Google or email when imem asks.

Free plan included. No card. No API key.

imem
Gemini
claude.ai
Claude
chatgpt.com
ChatGPT

Every tool forgets
what the others know.

Gemini here, Claude there, ChatGPT somewhere else. Every tool keeps its own slice of what you know — and none of them share.

imem connects
all of them.

Connect your tools to imem. Whatever you tell one, the others already know.

One memory
every tool shares.

Everything your AI learns lands in one place they all use — so you never have to repeat yourself again.

Open connector setup

Already living in the tools you use every day

Your team's knowledge
sits in silos.

Design, engineering and product each hold what they know in their own heads, docs and chats.

imem pools it
in one place.

Connect your team to imem, and what each person knows stops getting stuck in their head or buried in chats.

Everyone works from
the same memory.

Now everyone — and their AI — works from the same memory. Handoffs, onboarding and past decisions all live in one place.

Open connector setup
imem
MC
Maya Chen
Design
DP
Devin Park
Engineering
SL
Sara Liu
Product
imem
Design
Marketing
Finance

Every department
works in a silo.

Design, marketing and finance — each with its own files, decisions and history, walled off from the rest.

imem links
them together.

Connect every department to imem and the whole company draws from the same shared knowledge.

One shared memory,
company-wide.

What one team figures out, every other team can find — across projects, handoffs and the whole org.

Open connector setup

Your data, your keys

It's your memory. You hold the keys.

We won't overstate security, and we won't hide what the service reads. Your access is encrypted, scoped, revocable, and yours to export the day you decide to leave.

Encrypted coming and going

Your data travels over secure connections and sits encrypted when it's stored. Standard here, not an upsell.

Your keys stay your keys

Connections are scoped to your vault, revocable from settings, and never share raw auth tokens back to AI clients.

No security theater

We'll tell you straight: imem reads your vault so search, sync and your AI tools can do their job. We'd rather be clear than sound impressive.

Cut off any tool, instantly

Every connection is scoped to your vault and revocable from settings the moment you want it gone.


Why imem

One memory layer, not another silo.

Most AI memory lives inside one tool, behind an API key, in a store you can't read. imem is the opposite on every count.

With imem

  • One URL, OAuth in the browser — no API keys to paste
  • The same memory in Claude, ChatGPT, Cursor, Codex, Gemini, and Obsidian
  • A readable markdown wiki you can open, edit, and export anytime
  • Hybrid search: full-text plus semantic, over your own notes
  • A guided setup check proves memory works before you rely on it

A typical memory layer

  • Memory trapped inside a single AI tool
  • API keys copied into config files by hand
  • An opaque embeddings store you can't read or take with you
  • No way to confirm the memory actually works

Pricing

A shared memory for every tool — start free.

A private memory for your AI, real human support, and your data always yours to take with you. Free includes hosted MCP and hosted AI embeddings; upgrade to Solo, Team, or Business when you need higher limits or more room.

Free

A light private vault for getting imem installed and working.

$0/ month
Always availableno card
  • 1 private vault
  • Hosted MCP
  • Hosted AI embeddings
  • 1,000 MCP calls/mo
  • 500 searches/mo
  • 100 writes/mo
  • 50K embedding input tokens/mo
  • 128MB vault cap
Create free vault

Free plan. Upgrade only when you need more room.

Team

For small teams standardizing memory across shared AI workflows.

$99/ month
$990/yearsave $198
  • 125,000 MCP calls/mo
  • 40,000 searches/mo
  • 12,000 writes/mo
  • 10M embedding input tokens/mo
  • 5GB vault cap
  • Priority setup support
Try Team

14-day paid-plan trial. No card required to start.

Business

For business use with onboarding, security review support, and top self-serve limits.

$199/ month
$1,990/yearsave $398
  • 500,000 MCP calls/mo
  • 150,000 searches/mo
  • 50,000 writes/mo
  • 50M embedding input tokens/mo
  • 25GB vault cap
  • Onboarding/security review support
Try Business

14-day paid-plan trial. No card required to start.

Enterprise

For custom usage, security review, implementation planning, and procurement support.

Talkto us
Customhuman-led
  • Custom usage
  • DPA/security review
  • Implementation planning
  • Invoice and procurement support
Talk to us

No checkout. We'll scope the right plan with you.

Solo, Team, and Business are Stripe-backed self-serve plans with a 14-day no-card trial. Enterprise is handled by a human.


Questions, answered

What people usually ask before they try imem

Short answers in plain language.

imem is a private memory and wiki for your AI tools. It keeps your notes in plain markdown, lets your tools read and write that memory through MCP, and gives you a web app to manage everything.
You connect imem with one URL, approve access, and start using it. MCP is the connection underneath; you do not need to learn it first.
Built-in memory stays inside one tool. imem gives you one shared memory your AI tools can all use, and your notes stay in plain files you can export anytime.
No. imem works in the web app and through your AI tools on its own. Obsidian is optional if you want to edit the same markdown files locally.
Free includes 1 private vault, hosted MCP, hosted AI embeddings, 1,000 MCP calls/month, 500 searches/month, 100 writes/month, 50K embedding input tokens/month, and a 128MB vault cap.
Yes. Your vault stays in plain markdown, so you can export it and take your data with you at any time.

Connect imem. Share memory everywhere.

Add imem, paste one URL, and let every tool pick up exactly where the last one left off. About a minute to set up. The first time you don't have to repeat yourself, you'll get it.

Paste this into any AI chat · 3 steps · about 60 seconds · no API key
Open imem connector setup
Prefer to set it up manually?
MCP server URL · OAuth in the browser, no API key https://mcp.imem.ai

Step-by-step guides: Claude · ChatGPT · Cursor · Codex · Gemini · Obsidian

Claude / Connectors
Settings → Connectors
Add custom connector

Name: imem
URL: https://mcp.imem.ai

OAuth ready
Open Settings, choose Connectors, then add imem as a custom connector.
ChatGPT / Connectors
Settings → Connectors
Add connector → MCP server

Server URL:
https://mcp.imem.ai

Authorize the OAuth window.
Add an MCP connector, paste the imem URL, then authorize OAuth.
Gemini CLI / Terminal
$ gemini mcp add \\
  --transport http imem \\
  https://mcp.imem.ai

imem CONNECTED
tools: search, fetch, read_note, write_note
Gemini CLI connects through Streamable HTTP and discovers OAuth from imem.
Cursor / Settings / MCP
{
  "mcpServers": {
    "imem": {
      "url": "https://mcp.imem.ai"
    }
  }
}
Add imem in Cursor MCP settings, or paste the JSON into ~/.cursor/mcp.json.
Codex CLI / config.toml
[mcp_servers.imem]
url = "https://mcp.imem.ai"

Start Codex, ask it to use imem,
and approve the OAuth flow.
Add imem once to the Codex config; OAuth runs on the first tool call.
Generic MCP client / Remote HTTP
1. Add server
  https://mcp.imem.ai
2. Authorize — OAuth discovery
3. Enable tools — read / write

Avoid tokens in query strings.
Use the remote MCP URL with OAuth. Keep credentials out of query strings.