One shared memory for every AI you use, in plain Markdown files you own.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add callosium -- npx -y callosium --brain '<BRAIN>' --agent '<AGENT>' --token '<TOKEN>'~/.codex/config.toml
[mcp_servers.callosium]
command = "npx"
args = ["-y", "callosium", "--brain", "<BRAIN>", "--agent", "<AGENT>", "--token", "<TOKEN>"]
# codex mcp add callosium -- npx -y callosium --brain '<BRAIN>' --agent '<AGENT>' --token '<TOKEN>'~/.cursor/mcp.json
{
"mcpServers": {
"callosium": {
"command": "npx",
"args": [
"-y",
"callosium",
"--brain",
"<BRAIN>",
"--agent",
"<AGENT>",
"--token",
"<TOKEN>"
]
}
}
}.vscode/mcp.json
{
"servers": {
"callosium": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"callosium",
"--brain",
"<BRAIN>",
"--agent",
"<AGENT>",
"--token",
"<TOKEN>"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"callosium": {
"command": "npx",
"args": [
"-y",
"callosium",
"--brain",
"<BRAIN>",
"--agent",
"<AGENT>",
"--token",
"<TOKEN>"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"callosium": {
"command": "npx",
"args": [
"-y",
"callosium",
"--brain",
"<BRAIN>",
"--agent",
"<AGENT>",
"--token",
"<TOKEN>"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"callosium": {
"command": "npx",
"args": [
"-y",
"callosium",
"--brain",
"<BRAIN>",
"--agent",
"<AGENT>",
"--token",
"<TOKEN>"
]
}
}
}