Ariel Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 83 installs a week from npm. Last commit 1 Nov 2026.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
What the code does
We read the source, 3 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет mcp-ariel-memory ссылается на cipher208/mcp-ariel-memory
handler = logging.handlers.RotatingFileHandler(os.path.join(log_dir, rel_file), maxBytes=max_mb * 1024 * 1024, backupCount=backups)
subprocess.check_call([sys.executable, "-m", "pip", "install", *[spec for _, spec in absent]])
__import__(import_name)
description = "Private key path under .ssh/ — pairs a key artifact with where it lives"
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ariel-memory -- npx -y mcp-ariel-memory{
"mcpServers": {
"ariel-memory": {
"command": "npx",
"args": [
"-y",
"mcp-ariel-memory"
]
}
}
}[mcp_servers.ariel-memory]
command = "npx"
args = ["-y", "mcp-ariel-memory"]{
"mcpServers": {
"ariel-memory": {
"command": "npx",
"args": [
"-y",
"mcp-ariel-memory"
]
}
}
}{
"servers": {
"ariel-memory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-ariel-memory"
]
}
}
}Alternatives to Ariel Memory
same job, measured the same wayCognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.
Local-first RAG engine with MCP server for AI agent integration.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Rag Knowledge Graph MCP Server by MEOK AI Labs
AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Ariel Memory — questions
Answers built from our own checks of this server.