Memory types · Episodic
Episodic Memory in AI Agents
Episodic memory in AI agents stores specific past interactions and events — what happened, when and with whom — so the agent can reference particular experiences, not just general facts.
Episodic
“You called Tuesday about error 402”
Semantic
“User prefers phone support”
Definition
What is episodic memory in AI agents?
Episodic memory is event-specific, autobiographical memory — “remember when the user asked for a refund on March 3” — distinct from semantic memory (“user prefers email support”).
Also called interaction history or event logs. Tulving’s cognitive taxonomy maps episodic = particular experiences; semantic = general knowledge. Agents store episodic records with timestamps, session IDs and actor metadata.
Worked example
Episodic memory in a support agent
Tuesday 14:32 — user reports error ERR_PAYMENT_402 on checkout. Thursday 09:15 — user returns: “Is my refund processed?” The agent recalls Tuesday without re-asking.
{
"type": "episodic",
"timestamp": "2026-03-03T14:32:00Z",
"event": "User reported ERR_PAYMENT_402 on checkout",
"actors": ["user:48291", "agent:support-v2"],
"session_id": "sess_a8f2"
}The agent answers with Tuesday’s context — not a generic FAQ. → Customer support use case
Mechanism
How episodic memory is stored and retrieved
Conversation turns are chunked, timestamped and embedded — stored as vector records or graph event nodes, then retrieved by semantic similarity plus recency.
Scoring often follows Park et al. (2023): recency × importance × relevance, with recency decaying exponentially at 0.995 per hour since last access. Engram and Mem0 store episodic conversation memories in vector collections; Zep models temporal events as graph nodes with validity windows (Rasmussen et al., 2025).
Comparison
Episodic vs semantic memory
| Type | Example | Retrieval pattern |
|---|---|---|
| Episodic | “You called on Tuesday about error 402” | Time + event match |
| Semantic | “User prefers phone support” | Fact lookup |
Integration
Episodic, semantic and procedural memory together
Production agents tag memories by type in a unified store or split across collections — episodic for events, semantic for facts, procedural for skills.
Design pattern: single vector collection with memory_type metadata, or separate namespaces per type. Support bots combine episodic ticket history with semantic user preferences. Coding agents combine episodic session logs with semantic codebase facts.
FAQ
Frequently asked questions
What is an example of episodic memory in AI?
"User reported ERR_PAYMENT_402 on checkout, March 3 at 14:32" — a specific past event with timestamp. Contrast with semantic: "User prefers email support." See worked example above.
Episodic vs semantic memory — what's the difference?
Episodic = particular past events ("you called Tuesday"). Semantic = stable general facts ("user is vegetarian"). Both persist long-term but serve different retrieval patterns. See semantic memory.
Is episodic memory the same as conversation history?
Raw conversation history is unprocessed transcript. Episodic memory is usually extracted, timestamped event records — summarized facts about what happened, not every token. See writing memories.
Should episodic memory use a graph or vector store?
Vectors work for semantic search over event descriptions. Graphs (Zep Graphiti) excel when events involve changing relationships and validity windows. Engram and Mem0 use vector collections; Zep uses temporal graph nodes. See vector vs knowledge graph.
Does Zep store episodic memory?
Yes — Zep's temporal knowledge graph stores conversation-derived events and facts with bi-temporal validity. Ideal when account status or relationships change over time. See Zep alternatives.
Does Engram or Mem0 store episodic memory?
Both store conversation-derived episodic memories in vector collections scoped by user ID. Engram on Weaviate-native stacks; Mem0 via framework-agnostic API. See Engram explained.
How long should agents retain episodic events?
Depends on use case and policy — support bots may retain 90–365 days; assistants may summarize old episodes into semantic facts and evict raw events. See forgetting and eviction.
Episodic memory in multi-agent systems?
Tag episodes with agent_id and shared session_id. Multi-agent frameworks need explicit scoping so one agent's episodic record doesn't leak to another. See shared memory.
How is episodic memory retrieved?
Semantic search plus recency scoring — Park et al. (2023) uses recency × importance × relevance with 0.995/hour decay. Time filters narrow to recent sessions when needed. See memory retrieval.
Episodic memory for customer support bots?
Store ticket events (errors reported, refunds requested) with timestamps so follow-up sessions don't restart from zero. Combine with semantic prefs. See customer support use case.