Home / Product / How it works

The memory control plane, explained.

Prove what an agent knew, when it knew it, and that the record was never altered.

Architecture

Five layers, one API.

One engine: local library, self-hosted server, or managed cloud. Agents talk REST or MCP.

LayerWhat it does
LLM / AgentREST API or native MCP tool; durable facts are flushed to memory before the host framework compacts context.
Lians APIFastAPI: authentication, scopes, rate limiting, idempotency keys, OpenTelemetry traces.
Memories + Event LogEncrypted, bitemporal facts alongside an immutable SHA-256 hash chain.
Subject KeysPer-subject AES-256-GCM data-encryption keys, the targets of crypto-shred erasure.
StoragePostgreSQL 16 + pgvector (HNSW) for hybrid search; Redis as a hot cache.

Bitemporal model

Ask what was true, not just what is stored.

Every fact carries event time and system time. recall_at(...) reconstructs what an agent knew on a past date.

Recall pipeline

Hybrid search, validity-gated.

Hybrid retrieval is validity-gated so superseded versions stay out of current answers. If embeddings fail, results clearly report lexical-only fallback.

Review the evaluation →

Supersession pipeline

Revised facts close cleanly.

Stage 1 · Metadata overlap

Candidates are matched on structured keys (ticker, metric, subject) to find what could conflict.

Stage 2 · Deterministic decision

A rule engine classifies the relationship (SUPERSEDES, REFINES, CONFIRMS, or ADDS), fully reproducible, no model required.

Stage 3 · Optional LLM adjudication

An optional model stage resolves paraphrase-level conflicts; the superseded version closes but survives for audit.

Human review · Memory Governor

Low-confidence decisions queue in the console's Governance view. Confirm or reject with one click, audited either way.

Open conflicts stay loud

Unadjudicated conflicts ride at the top of every context block as explicit "X disagrees with Y" lines until someone resolves them.

Tamper-evident audit chain

Proof built into every write.

Each event enters a SHA-256 hash chain. Verify the record, reconstruct past state, or export a signed memory statement.

Flagship · Memory admission control

Govern what is allowed into memory.

Most memory layers write whatever the agent hands them. Lians puts a policy gate in front of the store.

Sensitive-data detection

PII, PHI, and MNPI are classified on the way in, handled by policy, not by accident.

Source-trust validation

Low-trust inputs don't silently become durable facts.

Prompt-injection quarantine

Suspicious instructions are held out of recall until reviewed.

Vagueness pre-filter

Too-vague candidates are rejected before they can dilute recall.

Review queue + modes

High-risk writes route to the console's Governance queue; run admission in off, monitor, or enforce mode.

Relationship graph

Compliance queries over bitemporal edges.

Edges are bitemporal too, so graph questions get the same point-in-time correctness as recall, with no separate graph database to operate.

OperationUse it for
relate(...)Record a temporal edge between two subjects.
path(...)Conflict-of-interest reachability: is attorney A connected to adverse party B?
neighbors(...)Related-party / beneficial-ownership and care-network analysis around a subject.

Build on memory you can defend.

Get an API key →