Cross-client AI memory hub — one physical SQLite, many clients. File-level pointers, REST API, Web Dashboard, MCP. Zero cloud. Dual-timeline governance. PyPI: memtether
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add memtether -- uvx memtether~/.codex/config.toml
[mcp_servers.memtether]
command = "uvx"
args = ["memtether"]
# codex mcp add memtether -- uvx memtether~/.cursor/mcp.json
{
"mcpServers": {
"memtether": {
"command": "uvx",
"args": [
"memtether"
]
}
}
}.vscode/mcp.json
{
"servers": {
"memtether": {
"type": "stdio",
"command": "uvx",
"args": [
"memtether"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"memtether": {
"command": "uvx",
"args": [
"memtether"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"memtether": {
"command": "uvx",
"args": [
"memtether"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"memtether": {
"command": "uvx",
"args": [
"memtether"
]
}
}
}