Content-addressed, ed25519-signed memory of every place on Earth. Apache-2.0, no keys for reads.
Content-addressed, ed25519-signed memory of every place on Earth. Apache-2.0, no keys for reads. That is what the emem — earth memory protocol mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
One click from the registry page adds the server to a supporting host. Nothing else is required: reads take no key, no account and no signup, so the first call works before you have decided whether to trust us. That is the point, and it is checkable rather than promised, because every answer carries an ed25519 receipt that verifies against the responder's published key rather than its word.
@vortxai/emem on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 7 tools. What each one is for:
high — frequency streams where signing overhead dominates the value,Token — What it namesdirect_sensor — measured, or read straight from the cited raw sourcedeterministic_index — recomputed by this responder from the cited parents. Exact for ops with nothing to accumulate; mean and sum over more than two parents compareattested_execution — produced inside a verified OS execution trace on an enrolled device, the output digest bound in the trace. Not recomputable by a third party, somodel_output — attributed, not checked. The responder signs that this attester claims V via recipe R. It never evaluated Vhuman_curated — a person asserted itThis sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Emem — Earth Memory Protocol's toolset — high, Token, direct_sensor and 4 more — is a fair guide to whether it matches your workflow. It is maintained by Vortx-AI; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| high | frequency streams where signing overhead dominates the value, |
| Token | What it names |
| direct_sensor | measured, or read straight from the cited raw source |
| deterministic_index | **recomputed by this responder** from the cited parents. Exact for ops with nothing to accumulate; mean and sum over more than two parents compare under a [stated 4-ULP window](docs/how-emem-compares.md#5b-what-verificat |
| attested_execution | produced inside a **verified OS execution trace** on an enrolled device, the output digest bound in the trace. Not recomputable by a third party, so deterministic: true excludes it |
| model_output | **attributed, not checked.** The responder signs that *this attester claims V via recipe R*. It never evaluated V |
| human_curated | a person asserted it |
{ "mcpServers": { "emem": { "type": "http", "url": "https://emem.dev/mcp" } } }Configuration as documented by the project. Restart the client after saving.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.