Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add caura -- python path/to/your/main.py~/.codex/config.toml
[mcp_servers.caura]
command = "python"
args = ["path/to/your/main.py"]
# codex mcp add caura -- python path/to/your/main.py~/.cursor/mcp.json
{
"mcpServers": {
"caura": {
"command": "python",
"args": [
"path/to/your/main.py"
]
}
}
}.vscode/mcp.json
{
"servers": {
"caura": {
"type": "stdio",
"command": "python",
"args": [
"path/to/your/main.py"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"caura": {
"command": "python",
"args": [
"path/to/your/main.py"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"caura": {
"command": "python",
"args": [
"path/to/your/main.py"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"caura": {
"command": "python",
"args": [
"path/to/your/main.py"
]
}
}
}