Skip to content
In development

MemX — Adaptive Memory Engine for AI

Zero-LLM-cost AI memory engine · bio-inspired forgetting curve · 12 PII filters

What is MemX?

MemX is Lurus’s adaptive memory engine for AI, built on ACE (Adaptive Context Engine)ACEAdaptive Context Engine. The core intelligence layer of MemX, comprising four modules: knowledge distillation, deduplication, decay, and retrieval.Learn more → v2.0. It provides AI agents with full knowledge lifecycle management: intelligent distillationKnowledge DistillationExtracting refined, reusable knowledge entries from large volumes of conversation. MemX's Reflector engine does this automatically.semantic deduplicationSemantic DedupSemantic deduplication, which uses cosine similarity to automatically identify and merge knowledge entries that mean the same thing but are worded differently. → decay-based forgetting → hybrid retrieval, giving AI a truly human-like "memory."

Three core advantages

  • Hybrid mode by default + automatic fallback — when the LLM is unavailable, it switches to pure rules: zero calls, zero cost.
  • Bio-inspired forgetting curve — Ebbinghaus exponential decay, half-life defaults to 30 days; strongly recalled items are promoted to permanent memory.
  • End-to-end privacy protection — sensitive information never enters the vector database.
12PII filter rulesnon-bypassable
4 layersHybrid retrievalL1→L4 weighted fusion
30 daysDecay half-lifedefault, configurable
Python · REST · MCPDelivery forms

Core Features

Four modules

From conversation to retrievable memory

For detailed rules, formulas, and parameters, see Core Concepts and Architecture.

Intelligent knowledge distillation (Reflector)

Hybrid mode (rule-based prefiltering + LLM refinement) identifies 5 knowledge patterns: error fixes / retry successes / config changes / new tool usage / repeated operations, scoring each 0-100 to filter out low-score noise.

Semantic deduplication and conflict detection (Curator)

Cosine similarity ≥0.8 auto-merges, 0.5-0.8 flags potential conflicts, below 0.5 is treated as independent knowledge.

Bio-inspired memory decay

7-day protection period + exponential decay + recall reinforcement; items retrieved more than 15 times are promoted to permanent memory and no longer decay.

Four-layer hybrid retrieval

L1 exact → L2 fuzzy → L3 metadata → L4 vector; after ScoreMerger weighted fusion, multiplied by DecayWeight × RecencyBoost × ScopeBoost, with automatic fallback when the vector layer is unavailable.

Privacy-first design

12 built-in sensitive-information filter rules (keys / tokens / database connection strings / local paths / custom regexes), automatically blocked before write.

Architecture Overview

Knowledge flows in from conversations and passes in turn through distillation, privacy filtering, and deduplication before landing in vector and metadata storage; retrieval requests go through the four-layer hybrid pipeline, while the decay engine continuously maintains memory activity in the background.

ACE engine data flow

Use Cases

Coding assistant

Remembers your coding habits, the pitfalls you’ve hit, and project conventions.

Customer support systems

Accumulates knowledge of customer interaction history to deliver personalized service.

Personal knowledge base

Automatically distills and organizes knowledge from everyday conversations.

Team collaboration

Shares team-level memory so new members can quickly get up to speed on context.

Comparison with Traditional Memory Systems

Why this is not just another vector store

维度MemX (ACE)Traditional approach (mem0)
Knowledge extractionHybrid engine (rule-based prefiltering + LLM refinement, reducing calls by 90%+)LLM (2-5K tokens each time)
DeduplicationCosine-similarity auto-mergeLLM judges item by item
ForgettingExponential decay + recall reinforcementPermanent storage, no eviction
SearchFour-layer hybrid searchVector search only
Privacy12 built-in sensitive-information filter rulesNo built-in protection
ScopeHierarchical (global / project / workspace)Flat (user / agent)
Token managementBuilt-in budget trimming (CJK-aware)Caller manages it themselves
Local embeddingsONNX local inference, fully offlineRequires an API

Next Steps

Next steps

Powered by Lurus Technologies