Lians Agent Memory

Lians is the system of record for AI in regulated industries: one append-only, tamper-evident, bitemporal, erasure-compatible ledger for what AI systems knew, did, and why.

The platform exposes two products on the same record layer:

• Memory — point-in-time-correct agent knowledge with supersession, provenance, information barriers, and crypto-shred erasure.

• Records — first-class inference, human-oversight, system-change, data-subject, incident, memory, and consequential-decision events, plus portable Evidence Pack exports.

Memory is what an agent knew. Records are what the AI system did. Either becomes evidence when a regulator, customer, validator, court, or auditor disputes an outcome.

The regulated AI record problem

Lians is the authoritative record layer for agents that operate on time-sensitive, audited, confidential data. The Memory product keeps context correct; the Records product captures behavior and oversight in an open, verifiable event format.

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

Related MCP server: Mnemic

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 use local persistent memory immediately or connect to a hosted Lians server. No SDK code, custom adapter, Docker service, URL, or API key is required for local mode.

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"]
    }
  }
}

Restart your client and Lians memory tools appear immediately. Local mode persists to ~/.lians/mcp.db. To use a hosted deployment instead, set LIANS_URL, LIANS_API_KEY, and optionally LIANS_AGENT_ID.

Any other MCP host

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

No environment variables are needed for local mode. Set LIANS_URL, LIANS_API_KEY, and optionally LIANS_AGENT_ID to use a remote server.

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:

• Legal — conflict-of-interest reachability (ABA 1.7/1.9): is an attorney connected to an adverse party?

• Finance — related-party / beneficial-ownership (SEC, AML/KYC): is a counterparty within N hops of a restricted entity?

• Healthcare — care-network / referral-pattern (anti-kickback) analysis.

mem.relate("analyst-1", src_entity="Attorney", rel_type="represented",
           dst_entity="ClientX", event_time=datetime(2026, 1, 1, tzinfo=timezone.utc))
mem.relate("analyst-1", src_entity="ClientX", rel_type="adverse_to",
           dst_entity="PartyY", event_time=datetime(2026, 1, 1, tzinfo=timezone.utc))

# Conflict-of-interest check — is there a connection, and through what?
path = mem.path("analyst-1", src_entity="Attorney", dst_entity="PartyY")
# → {"connected": True, "hops": 2, "path": [...]}

# Point-in-time: who was connected on the day of the trade?
mem.neighbors("analyst-1", entity="FundA", depth=2, as_of=datetime(2025, 6, 1, tzinfo=timezone.utc))

# Graph-proximity reranking — boost recalls about entities near an anchor
mem.recall_near("analyst-1", query="earnings", near_entity="FundA", near_key="ticker")

Endpoints: POST /v1/graph/relate · /v1/graph/unrelate · /v1/graph/extract (text → edges, rule-based or opt-in LLM) · GET /v1/graph/neighbors · /v1/graph/path (all as_of-capable). Inspired by Zep/Graphiti, built on our compliance spine.

Agent integrations — Claude Code, Codex, MCP

Give any coding agent persistent, compliance-grade memory:

Why Lians

Institutional AI agents accumulate facts that change over time: rate decisions supersede prior ones, guidance gets revised, medication doses change, care plans evolve, damages estimates move, and matter facts are corrected during discovery. Systems that return every version with equal rank contaminate the LLM context with stale facts.

Lians fixes this with a bitemporal model:

• event_time — when the fact happened (business time)

• valid_from / valid_to — when it was known (system time)

Superseded facts are excluded at the database layer. Every write is recorded in a tamper-evident SHA-256 hash chain (SEC 17a-4). Per-subject keys can be destroyed for GDPR erasure while the audit trail survives. Information barriers are enforced at PostgreSQL RLS, not the application layer.

How Lians compares

The two leading open memory layers each solve part of the problem; Lians is built for the regulated case where correctness, access, and auditability are all required at once.

vs mem0 — mem0's v3 is ADD-only, so revised facts (guidance, rates, doses, damages) pile up and contaminate recall; it has no documented encryption-at-rest, RBAC, or audit. Lians excludes stale versions deterministically and adds the compliance spine. → docs/compare-mem0.md

vs Zep / Graphiti — Graphiti's knowledge graph is excellent, and Lians now has one too (built on Postgres, no graph DB) — but Graphiti by its own docs has no access control, multi-tenancy, audit, or compliance; Zep only adds those in the closed cloud. Lians keeps the graph and the open compliance spine. → docs/compare-zep.md

→ Lookahead-bias demo — the same agent backtest with naive vs point-in-time retrieval (Sharpe 4.6 vs −0.6, every leak logged): ebeirne/lookahead-bias-demo · in-repo → Full benchmark numbers: docs/benchmark.md → Regulated-eval head-to-head (five compliance invariants, Lians 5.0 / Zep–Graphiti 2.0 / mem0 0.5): docs/regulated-eval-results.md — Lians, Graphiti OSS, and mem0 OSS all executed live in their default configurations (per-cell evidence in the appendix); remaining columns scored from their public API surface via runnable adapters you can re-run with keys.

Language SDKs

Lians ships native SDKs across five languages — the widest coverage of any open agent-memory layer. mem0 is Python/TypeScript; Zep adds Go. Lians matches all of those and adds Java and C, which neither competitor offers — putting the full compliance memory layer where regulated systems actually run: JVM risk platforms, and native/low-latency C in trading, market-data, and on-prem healthcare/legal stacks.

→ One-page install + 30-second quickstart for every language: docs/install.md

All five cover the same REST API: recall, point-in-time recall_at, snapshot, backtest, crypto-shred erasure, audit-chain verify, and the relationship graph (relate / neighbors / path).

Framework integrations

Self-hosted quickstart

git clone https://github.com/Lians-ai/Lians.git && cd Lians/agentmem
cp .env.demo .env
docker compose up --build -d
python scripts/seed_demo.py   # prints a demo API key; open demo/index.html

Deploy to Fly.io, Kubernetes, or bare Docker: docs/deploy.md

SDK reference

# All three clients share the same API surface
from lians import LiansClient          # sync, connects to hosted/self-hosted server
from lians import AsyncLiansClient     # async, for FastAPI / async frameworks
from lians import LocalLiansClient     # local SQLite, no server needed

client.add(agent_id, content, event_time, metadata={}, importance=0.5)
client.add_from_messages(agent_id, messages=[{"role": "user", "content": "..."}])
client.recall(agent_id, query, k=5)
client.recall_at(agent_id, query, as_of=datetime(...))   # point-in-time
client.snapshot(agent_id, as_of=datetime(...))           # full state export
client.backtest_check(agent_id, simulation_as_of=...)    # lookahead-bias detection
client.erase(subject_id, request_ref)                    # GDPR crypto-shred

Architecture

                    ┌──────────────┐
                    │  LLM / Agent │
                    └──────┬───────┘
                           │  REST / MCP
               ┌───────────▼────────────┐
               │        Lians API        │   FastAPI · rate-limit · OTEL
               └──┬────────────────┬────┘
          ┌───────▼──────┐  ┌──────▼───────┐
          │   memories    │  │  event_log   │
          │  (encrypted)  │  │ (hash chain) │
          │  bitemporal   │  │  append-only │
          └───────┬───────┘  └──────────────┘
                  │
          ┌───────▼───────┐
          │  subject_keys  │   AES-256-GCM per subject
          │  (crypto-shred)│   destroy key = content unrecoverable
          └───────────────┘

  Postgres 16 + pgvector (HNSW)      Redis (recall hot cache)

Recall pipeline: BM25 + cosine (Voyage Finance-2) → recency decay → validity gate (valid_to IS NULL for present; valid_from ≤ as_of < valid_to for point-in-time)

Supersession pipeline: Stage 1 (metadata key overlap) → Stage 2 (deterministic: SUPERSEDES / CONFIRMS / ADDS) → Stage 3 (optional LLM adjudication for paraphrase detection)

Configuration

Full reference: agentmem/.env.example

Key endpoints

Interactive docs: http://localhost:8000/docs

Running tests

cd agentmem
pip install -e ".[dev]"
pytest -v

# Benchmarks only (no API keys required)
pytest tests/test_supersession_benchmark.py tests/test_recall_quality.py -v

See docs/testing.md for the six named invariants (temporal soundness, audit immutability, erasure, etc.).

Production & operations

Built to run in a regulated production environment, not just to demo:

• Exactly-once writes — Idempotency-Key on POST /v1/memories; the SDKs send a stable key automatically, so a retried write never duplicates.

• Resilient clients — built-in retry with exponential backoff on transport errors / 5xx / 429.

• Kubernetes probes — cheap /livez (liveness) and deep /readyz (readiness), so a dependency blip doesn't restart healthy pods.

• Rate limiting — per-API-key sliding window (Redis), fails open.

• Access control — namespace-scoped keys, read/write/admin scopes, RBAC roles (owner/analyst/compliance/readonly), and SSO via gateway forward-auth.

• DB-layer information barriers — RESTRICTIVE PostgreSQL RLS, proven in CI against a non-superuser role. Run the app as a non-superuser DB role — superusers bypass RLS.

• Memory admission control — govern what's allowed into memory: PII/PHI/MNPI detection, source-trust, prompt-injection quarantine, and a high-risk review queue (ADMISSION_MODE). No other memory layer does this.

• SIEM streaming — every audit event forwarded to Splunk HEC / Datadog / Elastic (SIEM_URL), fire-and-forget.

• Observability — Prometheus metrics + Grafana, OpenTelemetry traces, JSON access logs with a request ID.

• Evaluation — a judge-free memory-eval harness (agentmem/benchmarks/memory_eval.py) in the LoCoMo/LongMemEval shape.

Security & procurement docs: security-whitepaper.md · threat-model.md · soc2-hipaa-readiness.md · sso.md · publishing.md

Compliance

Scope of these claims: Lians provides the technical controls mapped above — it is software, not a certification. Regulatory compliance is a property of your deployment and organization (retention configuration, policies, attestations such as SOC 2 or a HIPAA assessment), and several controls require operator configuration (WORM object-lock, non-superuser DB role, KMS). Every claim links to the doc that says exactly what is and isn't covered — start with soc2-hipaa-readiness.md.

Full documentation: compliance.md · hipaa.md · security-whitepaper.md · threat-model.md · soc2-hipaa-readiness.md · sso.md · worm-storage.md

Access control: namespace-scoped API keys with read/write/admin scopes and RBAC roles (owner/analyst/compliance/readonly); SSO via gateway forward-auth (any OIDC/SAML IdP).

Packaging & Pricing

Lians is open-source and fully self-hostable — the entire feature set, including every compliance primitive, is in this repository under Apache 2.0. Paid packages sell deployment support, hardening review, and evidence packets around the open core, not license keys. A managed cloud is in early access for customers whose compliance posture allows hosted processing (contact us); regulated buyers should choose the package by deployment boundary and evidence requirements, not by a consumer-style monthly tier.

Healthcare customers require an executed BAA before PHI is processed in a managed environment. Financial and legal customers may require customer-managed keys, private networking, regional residency, dedicated environments, or air-gapped deployment.

Full packaging documentation: docs/pricing-tiers.md and docs/billing.md

Switching from another system? Migrate from mem0 or Migrate from Zep CE

License

Apache 2.0 — see LICENSE.