Fleet-grade local memory for AI agents over plain Markdown — hybrid recall, multi-tenant, one process, no cloud/Docker/LLM
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add cogvault -- uvx cogvault --tenant '<TENANT>'~/.codex/config.toml
[mcp_servers.cogvault]
command = "uvx"
args = ["cogvault", "--tenant", "<TENANT>"]
# codex mcp add cogvault -- uvx cogvault --tenant '<TENANT>'~/.cursor/mcp.json
{
"mcpServers": {
"cogvault": {
"command": "uvx",
"args": [
"cogvault",
"--tenant",
"<TENANT>"
]
}
}
}.vscode/mcp.json
{
"servers": {
"cogvault": {
"type": "stdio",
"command": "uvx",
"args": [
"cogvault",
"--tenant",
"<TENANT>"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"cogvault": {
"command": "uvx",
"args": [
"cogvault",
"--tenant",
"<TENANT>"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"cogvault": {
"command": "uvx",
"args": [
"cogvault",
"--tenant",
"<TENANT>"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"cogvault": {
"command": "uvx",
"args": [
"cogvault",
"--tenant",
"<TENANT>"
]
}
}
}