Persistent memory · every model
One typed, audit-trailed memory of who you are and what you've decided — compressed into a current picture of you at session start, and saved and recalled in an instant across Claude, ChatGPT, Gemini, Claude Code and every model you use.
What it is
Every assistant starts each session blank, and each one keeps its own walled-off memory. Nuramem sits between you and every model as a shared layer: decisions, plans, people, references, learnings and current state — saved once, loaded everywhere, on every platform. It's not chat history and not notes — it's a strict, typed, contract-driven record you can audit.
One habit — name Nura, then say what you want
Naming Nura ensures it lands in your cross-model memory, not the assistant's own. Say it in Claude today; ask in ChatGPT or Gemini tomorrow — same memory, same answer. Nuramem also keeps up on its own — capturing the durable things as they come up and leaving the chit-chat alone.
One memory · every surface
Claude · ChatGPT · Gemini · Cursor
Add Nuramem as a connector in any MCP client — paste one URL, sign in once, and every conversation reads and writes your memory natively.
Connect your assistant →Where your team talks
Save a decision in the channel where it was made — recall it from any assistant later. One-click Slack install; Teams ships as an app package. Privacy-first: linked users only, capture opt-in per channel.
Add to Slack or Teams →macOS · menu bar
Chat with your memory from the menu bar, and capture from
anywhere with one keystroke — press ⌘⇧Space, type a thought,
it's saved. A calm once-a-day nudge when plans come due.
Terminal · scripts · CI
The nura CLI saves, searches and chats with the
same memory from any shell — and can auto-configure your MCP clients for
you.
app.nuramem.ai
See what your memory knows: browse and search every record, watch decisions evolve, confirm what's still true, manage shared projects and invites, export everything.
Open the app →Your data
Your memory lives in Nuramem's managed cloud storage — encrypted, isolated per user, and fast enough to load the moment you ask.
Export anytime · delete means deleted
Shared projects · now available
Personal memory is yours alone. Shared projects extend the same layer to a team: spin up a project, invite teammates by email, and the decisions, plans and context you agree on are recalled by everyone's assistant — on whichever model each person uses. Each member still keeps their own private personal memory; only what you put in the project is shared.
And when two people record conflicting decisions, Nuramem surfaces both — with who decided what — instead of silently picking a winner. It records the disagreement faithfully, so the team can resolve it on the record.
Create a project and invite your team from the web app, or just ask your assistant to "create a shared project." Invited teammates accept it from the app the next time they sign in.
Currently free for everyone
FAQ
The habit is naming Nura (or Nuramem) plus what you want: "nura, save this", "nura, remember the deadline moved to Friday", "nuramem, what's my latest decision on billing?", "nura, move these to the Acme project." Naming Nura is the part that matters — it ensures the memory lands in your cross-model layer instead of the assistant's own store.
It saves typed records — not chat logs — and at the start of a session hands the model a compact, current picture of who you are and what you're working on, on whichever model you're using.
No. Nuramem captures proactively: when you mention something durable — a decision, a deadline, a person and their role, a reference you're leaning on, a lesson learned, a change in your status — it saves it to the right place and tells you where, without being asked. When something's tentative or ambiguous it checks first, and it ignores passing chit-chat.
You're always in control: you can say "don't save that," browse and delete anything from the web app, and export or erase everything whenever you choose.
Any MCP-compatible client — we've verified Claude (Desktop, claude.ai, Claude Code),
ChatGPT and the Gemini CLI; Cursor, Windsurf, Zed and other MCP clients connect the
same way. Beyond assistants there's Slack, Microsoft Teams, the desktop app, the
nura CLI and a REST API — every surface reads and writes the same memory.
Step-by-step setup for each one lives on the Connect page.
Yes — that's shared projects, now available. Create a project in the web app (or just ask your assistant to "create a shared project"), then invite teammates by email and give each a role. They accept the invitation from the app the next time they sign in. One thing to know: the invitation is tied to the email address you send it to — your teammate needs to sign in with that address to see and accept it.
Once they're in, the decisions, plans and context recorded in that project are recalled by every member's assistant — on whichever model each person uses. Everyone keeps their own private personal memory; only what you put in the project is shared.
In Nuramem's managed databases on Google Cloud — encrypted in transit and at rest, isolated per user, and built so saves and recalls are instant. Synthesizing your records into the compact picture your assistant loads is the product, and it requires our systems to read your memory content — so we hold it, and we protect it accordingly. We never sell it and never use it to train AI models.
You stay in control in two concrete ways: export everything anytime from the web app, and delete means deleted — deleting your account physically erases your records, typically within a minute, with residual copies aging out of encrypted backups within seven days. Details in the Privacy Policy.
For MCP clients, no — you only ever paste the URL
https://mcp.nuramem.ai/mcp, and sign-in is OAuth (Nuramem never sees your
password). For calling the REST API directly, you authenticate with a bearer token:
sign in to the web app and copy it from
Developers → API access. The full tool surface is documented at
https://nuramem.ai/openapi.json.
MCP clients load Nuramem's tool list once, when the connection starts, and cache it for that session — so a newly added tool won't appear in a client you already had open. You don't need to remove and re-add the connector: just start a new chat or restart the client and it re-fetches the current tools. (Refreshing one app doesn't update another — each client keeps its own session.)
Nuramem is currently free — every feature, including shared projects and the Slack and Teams connectors. We expect to introduce paid plans later; if we do, we'll give notice before anything is charged. And you're never locked in: export your entire memory anytime.