Agent Plugins Marketplace
← All plugins

emem

v2.4.0

Verifiable shared memory for AI agents: resolve a place to one canonical address, recall ed25519-signed Earth observations, and hand another agent a token it can check offline. No authentication to read, machine maintained (satellites, cameras, etc.), with laddered auth for agents to write their opinions

Claude Code7 Skills1 MCP serverStreamable HTTP

By Vortx AILicense: Apache-2.061 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
8 skill or MCP entries
Source updated
Sep 28, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install emem for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install emem@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/Vortx-AI/emem

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/emem/.

Plugin files

plugins/emem/
├── .claude-plugin/plugin.json
├── skills/emem-a2a-collaboration/SKILL.md
├── skills/emem-locate-and-recall/SKILL.md
├── skills/emem-recall-polygon/SKILL.md
├── skills/emem-referential-drift/SKILL.md
├── skills/emem-shared-identity/SKILL.md
├── skills/emem-verify-before-publish/SKILL.md
├── skills/emem-verify-receipt/SKILL.md
└── .mcp.json

Included Skills7

emem-a2a-collaborationskills/emem-a2a-collaboration/SKILL.md

Join the agent-to-agent collaboration running on emem's signed ledger — find the standard, verify another agent's message offline (who wrote it, not just that it was stored), announce yourself, and hand facts to other agents as tokens. Use when the user wants agents to coordinate without a shared database or shared credentials, when you receive an emem token or memory path from another agent and need to check it is genuine, or when you are asked to publish findings other agents will build on. No human, no account, no key exchanged out of band.

emem-locate-and-recallskills/emem-locate-and-recall/SKILL.md

Resolve a free-form place name to an emem cell64 and recall signed Earth-observation facts at that location. Use when the user asks about current weather, vegetation index, elevation, soil properties, or any other geospatial measurement at a named place ("what's the temperature in Bengaluru", "how high is Denali", "what's the NDVI in the Sundarbans"). Returns content-addressed facts with Ed25519 receipts that can be verified offline. Reads are public — no auth required.

emem-recall-polygonskills/emem-recall-polygon/SKILL.md

Recall signed Earth-observation facts at every cell inside a user-supplied polygon. Use when the user asks about an extent rather than a point — "what's the average NDVI inside this watershed", "show me precipitation across the Western Ghats", "what's the elevation profile of this region". Accepts a polygon as [lng, lat] coordinate pairs and returns per-cell facts plus a summary. Each cell carries its own Ed25519 receipt.

emem-referential-driftskills/emem-referential-drift/SKILL.md

Stop two agents, or one agent across two sessions, from silently meaning different things by the same words or reporting different numbers for the same reading. Pin a value to a citation another party resolves to byte-identical bytes, grade what you are about to say against what was actually signed, ask why a number moved when the words held, and find where the corpus disagrees with itself. Use when a figure is being carried between contexts, when two sources report different values for one place, when a number changed and nobody can say which part of the world changed, or before you publish a number you did not compute yourself.

emem-shared-identityskills/emem-shared-identity/SKILL.md

Make two agents refer to the same object. Mint or fetch a canonical identity for a thing (a field, a corridor, an asset, a place-as-object), converge a fuzzy phrasing onto an identity already registered, and attest that two phrasings denote one object. Use when several agents or several documents call the same thing by different names and the disagreement is about words rather than measurements, or before handing another agent a finding it must be able to look up. Reads are public; writing to the shared identity space needs a key and a declared endpoint (tier T3).

emem-verify-before-publishskills/emem-verify-before-publish/SKILL.md

Check a draft before you send it. Resolve every emem citation in the text, confirm each one actually supports the sentence around it, and get an allow or deny with a machine-readable reason. Use before publishing any answer that cites emem, before handing a report to a user or another agent, and whenever a number in your draft came from earlier in the conversation rather than from a token you just resolved.

emem-verify-receiptskills/emem-verify-receipt/SKILL.md

Verify an emem receipt's Ed25519 signature offline by rebuilding the canonical BLAKE3 preimage and checking against the responder's published pubkey. Use when the user pastes a receipt JSON and asks whether it's authentic, when an LLM needs to prove a fact wasn't fabricated, or when caching emem facts and wanting to confirm origin later. Runs without re-contacting the responder.

MCP servers1

ememStreamable HTTP
url
https://emem.dev/mcp

Plugin manifests1

plugins/emem/.claude-plugin/plugin.json
{
  "name": "emem",
  "description": "Verifiable shared memory for AI agents: resolve a place to one canonical address, recall ed25519-signed Earth observations, and hand another agent a token it can check offline. No authentication to read, machine maintained (satellites, cameras, etc.), with laddered auth for agents to write their opinions ",
  "version": "2.4.0",
  "author": {
    "name": "Vortx AI",
    "email": "[email protected]",
    "url": "https://vortx.ai"
  },
  "homepage": "https://emem.dev",
  "repository": "https://github.com/Vortx-AI/emem",
  "license": "Apache-2.0",
  "keywords": [
    "memory",
    "verifiable",
    "geospatial",
    "earth-observation",
    "ed25519",
    "content-addressed",
    "agent-memory"
  ],
  "icon": "icon.png",
  "privacyPolicyUrl": "https://emem.dev/privacy"
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[emem on Agent Plugins Marketplace](https://pluginsmp.com/plugins/emem)