Lians — Financial Grade Agent Memory

Learn more - Docs - Install - Quickstart

Benchmark: 0 stale facts in top-5 vs mem0-style recall's 4/4, plus 100% supersession accuracy

Lians is regulated AI memory infrastructure: a memory control plane for agents that operate on time-sensitive, audited, confidential data.

The institutional memory problem

Lians should be understood as a memory control plane for agents that operate on time-sensitive, audited, confidential data.

Most memory layers help an agent remember. Lians is built for institutions that must also prove what the agent knew, when it knew it, where the fact came from, who was allowed to see it, whether stale facts were excluded, and whether erased content is cryptographically unrecoverable while the audit trail survives.

That is the gap between useful memory and deployable memory in financial, medical, and legal environments.

What regulated memory must prove

Generic agent memory optimizes for personalization and recall. Regulated agent memory has a different job: it must keep the agent's context correct, current, segregated, reproducible, and defensible under review.

Lians is designed for the failure modes that matter in institutions:

• Stale fact contamination - old rates, old guidance, old medication doses, old damages estimates, or old client facts must not silently enter context.
• Point-in-time reconstruction - an examiner, clinician, partner, or risk committee may ask what the agent knew at a specific timestamp.
• Information barriers - one desk, care team, or matter team must not read another team's memory because of an application-layer bug.
• Erasure with audit survival - private content must be removable without breaking custody records, audit hashes, or legal retention evidence.
• Relational compliance checks - conflicts of interest, related-party exposure, and referral networks are graph questions, not plain vector search.

The short competitive frame:

mem0 remembers. Zep connects. Lians proves what the agent knew, when it knew it, who could see it, and whether that memory was allowed to influence a regulated decision.

Built for regulated verticals

Procurement and technical review materials:

• Institutional proof kit
• Vertical pitch guide
• Competitive landscape
• Security whitepaper
• SOC 2 / HIPAA readiness
• Threat model
• Production deploy checklist

MCP - Native tool in any AI client

Lians is listed on the official MCP Registry. Any MCP-compatible host - Claude Desktop, Cursor, VS Code, Windsurf, and others - can connect to your Lians server as a native tool with a one-time config. No SDK code, no custom adapter, no wrapper.

Your agents get eight tools automatically:

Claude Desktop / Cursor / Windsurf

Add to your claude_desktop_config.json (or equivalent MCP config):

{
  "mcpServers": {
    "lians": {
      "command": "uvx",
      "args": ["--from", "lians-sdk[mcp]", "lians-mcp"],
      "env": {
        "LIANS_URL": "https://your-lians-server.internal",
        "LIANS_API_KEY": "lians_...",
        "LIANS_AGENT_ID": "trading-desk-1"
      }
    }
  }
}

Restart your client and Lians memory tools appear immediately — no install step for your users beyond setting the three env vars.

Any other MCP host

uvx --from 'lians-sdk[mcp]' lians-mcp

Set LIANS_URL, LIANS_API_KEY, and optionally LIANS_AGENT_ID in the environment.

Quickstart

pip install lians-sdk[local]   # zero-setup local mode (SQLite, no Docker)

from lians import LocalLiansClient
from datetime import datetime, timezone

mem = LocalLiansClient()

mem.add(
    agent_id="analyst-1",
    content="NVDA FY2026 revenue guidance raised to $40B",
    event_time=datetime(2025, 11, 19, 16, tzinfo=timezone.utc),
    metadata={"ticker": "NVDA", "metric": "revenue_guidance"},
)

# Superseded facts are excluded at the DB layer — never reach the LLM
results = mem.recall(agent_id="analyst-1", query="NVDA revenue guidance")

# Point-in-time: what did we know on March 1? (compliance-grade answer)
results = mem.recall_at(
    agent_id="analyst-1",
    query="NVDA revenue guidance",
    as_of=datetime(2025, 3, 1, tzinfo=timezone.utc),
)

Switch to the hosted server with one line: from lians import LiansClient as LocalLiansClient

Agent harness — drop-in memory loop

LiansMemoryHarness wraps the two operations every memory-augmented agent needs — recall-before and remember-after — into one object, with the compliance scoping (subject, source, event-time, information barrier) regulated deployments require. Works with any sync client (LiansClient or LocalLiansClient) and any model.

from lians import LiansClient, LiansMemoryHarness

harness = LiansMemoryHarness(mem, agent_id="research-desk", domain="finance")

# One call: recall context, run your model, persist the response.
answer = harness.run_turn(
    "What is NVDA's current revenue guidance?",
    generate=lambda context, query: call_model(f"{context}\n\nUser: {query}"),
)

# Or control each step:
context = harness.recall_context("NVDA revenue guidance")   # ready to inject
harness.remember("Desk note: guidance now $40B")            # write after the turn

Regulated scoping ties every write to one data subject and an information barrier:

harness = LiansMemoryHarness(
    mem, agent_id="care-team-3",
    subject_id="MRN-00042",       # per-subject key — the crypto-shred target
    barrier_group="oncology",     # information-barrier tag
    domain="healthcare",
)

Runnable end-to-end demo: agentmem/examples/harness_demo.py.

Relationship graph — compliance questions that are inherently relational

Some compliance checks are graph queries. Lians stores bitemporal relationship edges alongside facts — same audit chain, same information barriers, no graph database — so you can answer them point-in-time: