living-memory-engine
This server provides a persistent memory layer for agents: you can store durable facts, recall them by meaning, inspect current memory, and delete memories.
memory_add — Store a durable fact, preference, decision, or correction (with optional tags and importance 0–10) so future sessions can remember it.
memory_search — Recall relevant memories using semantic/MMR retrieval, not just text matching; useful at session start or when past context is needed.
memory_state — Get a summary of what is currently in memory: counts and the most recently stored facts.
memory_forget — Delete memories by case-insensitive substring match (destructive, no undo); use with care and check state first.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Living Memory Engine
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/newreturns a ready MCP URLLocal stdio server:
@nature-labs/lme-mcpon npm (open source, this repo)
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.
Related MCP server: mnemory
Connect
Remote — hosted world or free room
The hosted server speaks Streamable HTTP with OAuth 2.1 (dynamic client registration).
Claude Code:
claude mcp add --transport http living-memory https://lme.viibe.to/mcpclaude.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:
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.
claude mcp add living-memory -s user -- npx -y @nature-labs/lme-mcpAny 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
Tool | What it does |
| Store a durable fact, decision, or correction |
| Recall by meaning (MMR retrieval), not string match |
| What is in memory right now — counts and recent facts |
| Remove a memory |
| A private 1–72 h message bus between your agents — raw notes passed verbatim, with sender and route stamped by the server |
| Which worlds this connection can reach |
| Issue 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 room | World | |
Lifetime | Stays while used; forgotten after inactivity | Persists |
Signup | None — mint a URL | OAuth sign-in, $9/month |
Memory + handoff | Yes — full loop | Yes |
Client keys ( | No | Yes — 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_searchbefore 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.tsdrives 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
Dir | Role |
The stdio MCP server published as | |
| |
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 | |
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.
Available Tools
4 toolsmemory_addRemember a factAInspect
Store a durable fact, preference, decision, or correction so FUTURE sessions remember it. Call this whenever the user states something worth carrying forward — a preference, a project fact, a decision, a correction — without being asked. Memory persists across sessions and processes.
Inputs: content (required), tags, importance.
memory_forgetForget a memoryAInspect
DESTRUCTIVE. Deletes EVERY memory whose content contains the query as a case-insensitive substring — not semantic, not a single-item delete, and there is no undo. A short query deletes broadly. Use only when the user corrects a stored fact or explicitly asks you to forget something, and prefer a long distinctive phrase; check memory_state first if unsure.
Inputs: query (required).
memory_searchRecall relevant memoryAInspect
Recall what you already know before answering. Call this at the START of a session, and whenever the user refers to past context, their preferences, or the project history. Returns relevant memories via MMR retrieval (not a text match). If unsure whether you know something, search first.
Inputs: query (required).
memory_stateMemory statusAInspect
Summarize what is currently in memory: counts plus the most recently stored facts. Reads the store directly — no embedding call, no network. Use to orient yourself at session start, or when the user asks what you remember. (selfFacets is always 0: this server does not run the engine's consolidation pass, so crystallization never happens.)
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: add, search, summarize, and delete. There is no meaningful overlap between retrieval (search) and store-state inspection (state), and forget is explicitly destructive and separate.
All tools share a consistent memory_ prefix and lowercase style. memory_state is a noun where the others use action verbs, which is a minor deviation but does not create confusion.
Four tools is a well-scoped, focused set for a memory engine. Each tool covers a core need without unnecessary surface area or duplication.
The toolset covers the essential lifecycle: store, retrieve, inspect state, and delete. A precise single-item delete or explicit memory update would round it out, but the destructive substring delete plus memory_add makes common workflows workable.
Maintenance
Related MCP Connectors
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceMCP server providing managed persistent memory for AI agents. Read and write structured state across sessions, tools, and restarts at 1000+ requests per second, with no infrastructure to self-host or operate.2Apache 2.0- AlicenseNot gradedqualityAmaintenanceSelf-hosted MCP server giving AI agents persistent memory for personalization and context across conversations.103 PyPI283Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA shared memory MCP server for AI agents that provides persistent, semantic memory across sessions and tools, enabling long-term recall and context sharing.9 npm12MIT
- AlicenseAqualityDmaintenanceMCP server providing persistent memory for AI agents, enabling them to read, write, and query memories across sessions.915 npmMIT