Shared memory for every AI agent in your terminal: Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI, OpenCode. Verbatim, on your own PC, zero model calls to save; 88.8% on LongMemEval.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add graph-mind -- uvx graph-mind-memory~/.codex/config.toml
[mcp_servers.graph-mind]
command = "uvx"
args = ["graph-mind-memory"]
# codex mcp add graph-mind -- uvx graph-mind-memory~/.cursor/mcp.json
{
"mcpServers": {
"graph-mind": {
"command": "uvx",
"args": [
"graph-mind-memory"
]
}
}
}.vscode/mcp.json
{
"servers": {
"graph-mind": {
"type": "stdio",
"command": "uvx",
"args": [
"graph-mind-memory"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"graph-mind": {
"command": "uvx",
"args": [
"graph-mind-memory"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"graph-mind": {
"command": "uvx",
"args": [
"graph-mind-memory"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"graph-mind": {
"command": "uvx",
"args": [
"graph-mind-memory"
]
}
}
}