A high-performance, **pure Rust** Model Context Protocol (MCP) server that provides persistent, semantic, and graph-based memory for AI agents.
A high-performance, pure Rust Model Context Protocol (MCP) server that provides persistent, semantic, and graph-based memory for AI agents.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"memory": {
"command": "docker",
"args": [
"run",
"--init",
"-i",
"--rm",
"--memory=3g",
"-v",
"mcp-data:/data",
"-v",
"/absolute/path/to/your/project:/project:ro",
"ghcr.io/pomazanbohdan/memory-mcp-1file:latest"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Enables Claude, and other Model Context Protocol (MCP) clients, to manage and access memories stored in a simple text file for enhanced context
Example MCP server demonstrating framework usage
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.