Local institutional memory for agents where BFT consensus among validators approves every memory before it is committed.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add sage -- docker run -i --rm ghcr.io/l33tdawg/sage:11.24.1~/.codex/config.toml
[mcp_servers.sage]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/l33tdawg/sage:11.24.1"]
# codex mcp add sage -- docker run -i --rm ghcr.io/l33tdawg/sage:11.24.1~/.cursor/mcp.json
{
"mcpServers": {
"sage": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:11.24.1"
]
}
}
}.vscode/mcp.json
{
"servers": {
"sage": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:11.24.1"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"sage": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:11.24.1"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"sage": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:11.24.1"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"sage": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:11.24.1"
]
}
}
}