A local-first, LLM-agnostic memory layer for AI assistants
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add memento -- npx -y @psraghuveer/memento~/.codex/config.toml
[mcp_servers.memento]
command = "npx"
args = ["-y", "@psraghuveer/memento"]
# codex mcp add memento -- npx -y @psraghuveer/memento~/.cursor/mcp.json
{
"mcpServers": {
"memento": {
"command": "npx",
"args": [
"-y",
"@psraghuveer/memento"
]
}
}
}.vscode/mcp.json
{
"servers": {
"memento": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@psraghuveer/memento"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"memento": {
"command": "npx",
"args": [
"-y",
"@psraghuveer/memento"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"memento": {
"command": "npx",
"args": [
"-y",
"@psraghuveer/memento"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"memento": {
"command": "npx",
"args": [
"-y",
"@psraghuveer/memento"
]
}
}
}