{
  "id": "agent-memory",
  "code": "PTL-0071",
  "term": "Agent Memory",
  "aliases": [
    "long-term memory",
    "memory stream"
  ],
  "category": "agents",
  "definition": "Agent memory is the set of mechanisms that let a language-model agent store information beyond a single context window, such as conversation summaries, retrievable records of past events, and reflections, and bring the relevant parts back into context later.",
  "description": "Park et al.'s generative agents scored memories by recency, importance, and relevance and periodically synthesized higher-level reflections. MemGPT treated the context window like main memory and paged information in and out of external storage.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "ai-agent",
    "context-engineering",
    "reflexion",
    "retrieval-augmented-generation"
  ],
  "introduced": null,
  "sources": [
    {
      "title": "Generative Agents: Interactive Simulacra of Human Behavior",
      "authors": "Park et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2304.03442"
    },
    {
      "title": "MemGPT: Towards LLMs as Operating Systems",
      "authors": "Packer et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2310.08560"
    }
  ],
  "url": "https://protologue.com/t/agent-memory/",
  "citation": "Protologue. (2026). Agent Memory. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0071). https://protologue.com/t/agent-memory/"
}