> For the complete documentation index, see [llms.txt](https://docs.living-memory.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.living-memory.app/local.md).

# Local engine & local MCP

Choose local execution when you want to manage the memory store and runtime on your machine.

| Package                             | Role                                                           |
| ----------------------------------- | -------------------------------------------------------------- |
| `@nature-labs/living-memory-engine` | Framework-independent memory engine for application developers |
| `@nature-labs/lme-mcp`              | Local stdio MCP server launched by an agent client             |
| `@nature-labs/living-memory-js`     | Client for an existing hosted Space                            |

The local MCP package is pre-alpha. It uses a local snapshot file and offers memory add/search/state/forget. It does not provide the hosted handoff workflow in this guide.

## Start with the package guide

Give your coding agent this instruction:

```
Read the @nature-labs/lme-mcp package README. Help me install it,
run its bundled smoke test, choose an embedding configuration,
and connect it to my MCP client. Confirm whether the embedder is
real or mock before describing recall as semantic.
Ask before changing existing configuration outside this setup.
```

Expected result: the subprocess starts, the client discovers memory tools, and the package smoke test passes. Real semantic recall also requires a working real embedding configuration.

Local storage does not guarantee offline operation: remote embedding providers receive embedding requests. The mock mode does not provide semantic retrieval. Keep separate snapshots for incompatible embedding configurations.

Local files and hosted capsules are separate stores. Installing the local package does not import your hosted memories.

See [the local MCP package guide](https://github.com/v1b3x0r/living-memory-engine/tree/main/lme-mcp) and [engine documentation](https://github.com/v1b3x0r/living-memory-engine/tree/main/engine) for configuration. A full self-hosting guide is outside this first-use edition.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.living-memory.app/local.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.