Lians Agent Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 62 installs a week from pypi. Last commit 21 Sep 2026.
Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
subprocess.Popen( # noqa: S603
ProcessStartInfo start = new ProcessStartInfo();
child = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add lians -- uvx lians-sdk
{
"mcpServers": {
"lians": {
"command": "uvx",
"args": [
"lians-sdk"
]
}
}
}
[mcp_servers.lians]
command = "uvx"
args = ["lians-sdk"]
{
"mcpServers": {
"lians": {
"command": "uvx",
"args": [
"lians-sdk"
]
}
}
}
{
"servers": {
"lians": {
"type": "stdio",
"command": "uvx",
"args": [
"lians-sdk"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
LIANS_URL (Optional base URL of a hosted or self-hosted Lians server; omit for local SQLite mode), LIANS_API_KEY (API key with read and write scopes), LIANS_AGENT_ID (Agent identifier used as the memory namespace), LIANS_LOCAL_DB (Local SQLite path used when LIANS_URL is omitted), LIANS_NAMESPACE (Local tenant namespace).
Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.
Causal memory and tamper-evident audit log for AI agents: log, why, search, time travel.
Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
Persistent memory for AI agents. Memories decay with time and strengthen on recall.
Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage.
Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage.
Answers built from our own checks of this server.