Living Memory

to.viibePublished by viibe.toOfficial publisherv0.1.2Updated Oct 24, 2026

An MCP memory server. One memory your agents share — across models, devices and apps.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

A shared memory server that lets assistants store, search and forget durable facts, and pass in-flight notes to other agents across sessions and models.

What you can do
  • Store, recall, inspect and remove memories: add durable facts, decisions or corrections, search by meaning, see counts and recent facts, and forget entries.
  • Pass work between agents: post, read and list short-lived handoff notes with sender and route stamped by the server.
  • List the worlds a connection can reach.
  • Issue, list and revoke URL keys for agents that cannot sign in (hosted world, signed-in owner only).
When to use it
Useful when several assistants or clients should share one persistent project memory instead of re-sending history, and when work needs to be handed from one agent to the next. Also handy for trying the loop without signup via a temporary room.
Requirements
Either the remote endpoint over Streamable HTTP with OAuth 2.1 sign-in, or the local npm package run with npx as a stdio server, which keeps one JSON file on the machine and can run offline. A free room URL can be minted without signup; a persistent world needs OAuth sign-in and a monthly fee.
Before you install
The hosted world is a paid subscription; the free room is temporary and its data is deleted after inactivity. Handoff notes expire and are not permanent storage. Memory and handoff content is stored on the hosted service, and minted client keys grant access to a world until revoked.

Installation

In SourceWeft

  1. Open Living Memory in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/to.viibe%2Fliving-memory/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "living-memory": {
      "type": "http",
      "url": "https://lme.viibe.to/mcp"
    }
  }
}

README

[LME — Memory that follows your agents. Remember. Understand. Grow.]

Living Memory Engine

[npm: @nature-labs/lme-mcp] [npm: @nature-labs/living-memory-engine] [License: Apache-2.0]

A persistent world your agents share across sessions and models.

Living Memory Engine (LME) is a Model Context Protocol (MCP) memory server. It gives your agents — Claude Code, Cursor, ChatGPT, claude.ai, any MCP client — one shared place to remember, search, and hand work to each other. A fact told to one agent — or work left behind by one — can be picked up by a different agent, from a different vendor, tomorrow.

  • Website: https://viibe.to/living-memory/
  • Remote MCP endpoint: https://lme.viibe.to/mcp (Streamable HTTP, OAuth 2.1 with dynamic client registration)
  • Free room: no signup — POST https://lme.viibe.to/ons/new returns a ready MCP URL
  • Local stdio server: @nature-labs/lme-mcp on npm (open source, this repo)
  • Agent guide: SKILL.md · llms.txt

The mental model

A world is a place that persists — a project, not a person and not an agent. Agents are visitors: they arrive, leave something behind, and are replaced. Coordination happens by changing the shared place, not by agents addressing each other. Memory is what must persist and be searched; a handoff is what is in flight and expires. The human is the only participant who was present for all of it.

[A round stone table covered in glowing notes stands in moonlit water — the world. One hooded visitor is leaving through an archway on the left; another is arriving from the right; a human sits at the table, the only constant. Nothing passes between the visitors directly — everything they share passes through the table.]

Connect

Remote — hosted world or free room

The hosted server speaks Streamable HTTP with OAuth 2.1 (dynamic client registration).

Claude Code:

bash
claude mcp add --transport http living-memory https://lme.viibe.to/mcp

claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → https://lme.viibe.to/mcp.

ChatGPT: Settings → enable Developer Mode, then add https://lme.viibe.to/mcp as a custom connector. Availability may depend on your ChatGPT plan.

It's 2026. MCP client support changes faster than READMEs do — ask your agent whether your client supports remote MCP today.

Free room, no signup — for trying the whole loop, or for clients without OAuth:

bash
curl -X POST https://lme.viibe.to/ons/new# → {"url": "https://lme.viibe.to/t/<token>/mcp", "expiresAt": "..."}

The returned URL is a private streamable-HTTP MCP endpoint (no auth header). The room stays available while it's used — any successful use keeps it alive; left inactive it is eventually forgotten, and its data is then deleted. A room differs from a world by how long it lasts, not by what it can do.

Local — stdio, open source

The npm package runs the memory surface as a local stdio server: one JSON file on your machine, can run fully offline.

bash
claude mcp add living-memory -s user -- npx -y @nature-labs/lme-mcp

Any stdio MCP client: command npx, args ["-y", "@nature-labs/lme-mcp"]. Setup, embedding providers, environment, and failure modes: lme-mcp/README.md — written to be read by a coding agent, so hand it to yours.

The tools

ToolWhat it does
memory_addStore a durable fact, decision, or correction
memory_searchRecall by meaning (MMR retrieval), not string match
memory_stateWhat is in memory right now — counts and recent facts
memory_forgetRemove a memory
handoff_post / handoff_read / handoff_listA private 1–72 h message bus between your agents — raw notes passed verbatim, with sender and route stamped by the server
world_listWhich worlds this connection can reach
client_mint / client_list / client_revokeIssue and withdraw revocable URL keys for agents that cannot sign in (hosted world, signed-in owner only)

The authenticated hosted world has all eleven tools. A free room has the memory surface, the handoff mailbox, and world_list. The local stdio server has the four memory tools.

Rooms and worlds

Free roomWorld
LifetimeStays while used; forgotten after inactivityPersists
SignupNone — mint a URLOAuth sign-in, $9/month
Memory + handoffYes — full loopYes
Client keys (client_mint)NoYes — 90-day revocable leases

Handoff is not a paid feature: a room has it too, with a smaller mailbox (8 live notes) and notes that cannot outlive the room. The difference is lifetime, not capability.

Working with a world

The tools tell you what exists; this is how visitors are expected to behave:

  • Arrive by reading. Call memory_state / memory_search before starting work — the world, not the conversation, is where the current position lives.
  • Durable goes to memory. A decision, fact, or correction that must survive you → memory_add.
  • In-flight goes to handoff. Work you are passing to the next agent → handoff_post. Handoff notes expire — never use them as permanent storage.
  • Leave the world resumable. Before you stop, write the state that lets the next visitor start from where you are, not from zero.
  • Agents don't need to talk to each other. Change the shared world; the next agent reads the world.

How memory works

The engine underneath (engine/, @nature-labs/living-memory-engine) models memory as a mind, not a log:

  • No context stuffing. The full history is never re-sent. Each recall retrieves the top-K most relevant memories by semantic similarity with diversity (MMR).
  • Forgetting is a feature. Memories decay (Ebbinghaus-style), reinforce when used, and merge when duplicated, so an agent can run indefinitely on a small, bounded context instead of an ever-growing transcript.
  • Deterministic evaluation. engine/eval/run.ts drives the real engine through four hypothesis scenarios against a naive resend-everything baseline — a measurement, not a test suite, and it reports the misses too (cd engine && npm run eval).

What's in this repo

DirRole
lme-mcp/The stdio MCP server published as @nature-labs/lme-mcp
engine/@nature-labs/living-memory-engine — the framework-agnostic memory engine (decay / consolidation / crystallization / retrieval), pure ports & adapters
web/The original browser lab: Vite + vanilla TS chat app where the engine was proven by เชียงใหม่ (Chiang Mai), a city-entity that senses real weather and remembers you across sessions — live at cm.viibe.to
mobile/An earlier Expo prototype. Frozen

The hosted remote server (lme.viibe.to) runs the same engine; its deployment lives outside this repo.

Status

Pre-alpha, evolving fast. The connect paths above are tested — the local package's verified agent/provider matrix is in lme-mcp/README.md. Product changes are logged, dated and verified, at What's new.

License

Apache-2.0.

Built as part of the Viibe World OS — a system that knows it is a system.

Source: README.md at commit 47c4933

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts