memory vs samyama-graph
Side-by-side comparison to help you pick between these two MCP servers.
memory by modelcontextprotocol | samyama-graph by samyama-ai | |
|---|---|---|
| Stars | ★ 85,748 | ★ 62 |
| 30d uses | — | — |
| Score | 77 | 48 |
| Official | ✓ | — |
| Categories | Knowledge GraphAI / LLM ToolsProductivity | DatabaseKnowledge GraphAI / LLM Tools |
| Language | TypeScript | Rust |
| Last commit | this month | this month |
memory · Summary
An MCP server implementing persistent memory using a local knowledge graph for AI models to remember user information across chats.
samyama-graph · Summary
High-performance graph-vector database with MCP server support for natural language queries over knowledge graphs.
memory · Use cases
- Personalizing AI assistant interactions by remembering user preferences, history, and relationships
- Building context-aware chat applications that maintain conversation history
- Creating knowledge bases that persist across AI model sessions
samyama-graph · Use cases
- Biomedical research by querying interconnected medical literature, clinical trials, and drug interactions
- Enterprise knowledge graphs with automatic MCP server generation for AI agents
- Large-scale graph analytics with parallel algorithms for social networks or fraud detection
memory · Install
Installation
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}VS Code
Use one-click installation buttons or manually configure in .vscode/mcp.json:
{
"servers": {
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}Docker
{
"mcpServers": {
"memory": {
"command": "docker",
"args": ["run", "-i", "-v", "claude-memory:/app/dist", "--rm", "mcp/memory"]
}
}
}samyama-graph · Install
# Install Samyama
git clone https://github.com/samyama-ai/samyama-graph && cd samyama-graph
cargo build --release
./target/release/samyama # Starts RESP on :6379 and HTTP on :8080
# Install the MCP server
pip install samyama[mcp]
# Start an MCP server with demo data
samyama-mcp-serve --demo cricketFor Claude Desktop integration:
{
"mcpServers": {
"samyama": {
"command": "python",
"args": ["-m", "samyama.mcp"],
"env": {}
}
}
}