Overview

The Problem

AI agents lose context between sessions. They cannot remember what a user told them last week, build up domain knowledge across conversations, or track how information changes over time.

The Solution

MemLayer is a persistent memory system for AI agents. It provides a knowledge graph that agents can read from and write to through MCP or a REST API.

When an agent stores a memory, MemLayer extracts structured facts, classifies them into semantic layers, connects them to existing knowledge, and tracks when each fact was recorded. When the agent recalls something, MemLayer combines vector similarity search with graph traversal to find relevant memories — even ones that don’t directly match the query.

Key Capabilities

Automatic extraction — When content is stored, an LLM breaks it into atomic facts and determines how each fact relates to existing knowledge.

Semantic search — Memories are embedded as vectors. Recall queries use cosine similarity to find conceptually related memories, not just keyword matches.

Temporal queries — Datahike tracks the full transaction history. The as-of parameter lets agents query what the knowledge graph looked like at any past point in time. See Temporal Queries.

Knowledge graph with semantic layers — Memories are organized in a four-layer hierarchy from abstract domains to specific episodes. This improves recall by providing multiple paths to find information. See Semantic Layers.

Per-agent memory namespaces — Each agent operates in isolation with its own knowledge graph. No cross-contamination between agents.

Four Operations

Operation	Purpose	Description
Retain	Store	Ingest content with automatic extraction, deduplication, and relationship creation
Recall	Search	Find relevant memories using semantic search, graph traversal, and temporal filtering
Reflect	Organize	Analyze the knowledge graph to create missing layers, draw inferences, and restructure relationships
Forget	Delete	Remove a memory from active queries so it no longer appears in recall results

Architecture

                    ┌─────────────────┐
                    │   AI Agent      │
                    │  (MCP / REST)   │
                    └────────┬────────┘
                             │
                    ┌────────▼────────┐
                    │  MemLayer API   │
                    │   (Clojure)     │
                    └──┬─────┬─────┬──┘
                       │     │     │
              ┌────────▼┐ ┌──▼───┐ ┌▼────────┐
              │Datahike │ │Proxi-│ │ LLM APIs│
              │(datalog │ │mum   │ │(OpenAI, │
              │  DB)    │ │(vec) │ │ Groq)   │
              └─────────┘ └──────┘ └─────────┘

• Datahike — Embedded datalog database for memories, relationships, and graph structure.
• Proximum — Embedded vector database for semantic similarity search.
• LLM APIs — OpenAI for embedding generation, Groq for LLM inference (entity extraction, layer classification, decision-making).