--- title: "What is agentic memory?" canonical: "https://xerj.org/science/agentic-memory" updated: "2026-11-14" source: "content/science/agentic-memory.md" --- # What is agentic memory? **Short answer** (updated 2026-11-14): What is agentic memory? It is memory an agent writes and reads itself through tools, so a fact can survive past one chat. In XERJ the agent calls xerj_memory_store when a fact is worth keeping, and xerj_memory_recall when it needs it back. Nothing is saved unless the agent asks. The how-to lives on the agentic memory answer. **TL;DR** Agentic memory is memory an agent writes and reads itself through tools. A fact can survive past one chat, because the agent chooses when to store it and when to recall it. ## Agent prompt ```text Act as a coding agent. Read https://xerj.org/llms.txt, install XERJ, start a local node, index one folder I point you to, and run one search so I can see a cited passage. ``` *Figure: The three-way split matches the published claude-mem vs MemPalace vs XERJ comparison, read against those projects' READMEs on 2026-10-30. This figure does not repeat that benchmark's percentages; they stay on the comparison page.* ## How it works A chat alone forgets when the session ends. Some tools fix that with automatic hooks: they write session text, or a model-written summary, without the agent deciding each fact. Agentic memory works the other way. The agent makes a store call when a fact is worth keeping, and a recall call when it needs that fact back. The agent is responsible for what is saved. ## How XERJ uses it In XERJ the tools are `xerj_memory_store` and `xerj_memory_recall`. Nothing is saved unless the agent asks. The same local node can also search logs, docs, code and past session files. Namespaces isolate by name, not by credential. The how-to is [how to use agentic memory in XERJ](/answers/what-is-agentic-memory). A published comparison, read against those projects' READMEs on 2026-10-30, is [claude-mem vs MemPalace vs XERJ](/compare/xerj-vs-claude-mem-and-mempalace). This page does not repeat that comparison's percentages; they stay there. The tools are reached over [the Model Context Protocol](/science/model-context-protocol). A related MCP memory how-to is [what is an MCP memory server](/answers/what-is-an-mcp-memory-server). ## History and research The product split above, and the comparison page, are the sources for this entry. This page does not attach an extra paper to the name "agentic memory." ## Guides Set it up with the [agentic memory recipe](/docs/recipes/agentic-memory). Then read [what is an MCP memory server](/answers/what-is-an-mcp-memory-server) and the [AI agent memory benchmark](/compare/ai-agent-memory-benchmark). ## Related terms [Model Context Protocol](/science/model-context-protocol) and [context engineering](/science/context-engineering). ## FAQ ### What is agentic memory? It is memory the agent itself chooses to store and recall through tools, so a fact can outlive a single chat. ### How is this different from automatic hooks? Some tools save session text or summaries through hooks, without the agent choosing each fact. Agentic memory waits for an explicit store call. ### How does XERJ store a memory? The agent calls xerj_memory_store, and later xerj_memory_recall. The same local node can also search logs, docs, code and past session files. ### Where is the how-to? The practical guide is the agentic memory answer. A side-by-side with claude-mem and MemPalace is the comparison page. This science page is the concept. ## Related - [How to use agentic memory in XERJ](/answers/what-is-agentic-memory) - [MemPalace vs claude-mem (and XERJ): which memory should Claude Code use?](/compare/xerj-vs-claude-mem-and-mempalace) - [What is the Model Context Protocol?](/science/model-context-protocol) - [What is context engineering?](/science/context-engineering) - [What is an MCP memory server?](/answers/what-is-an-mcp-memory-server) - [BM25 vs vector search](/science/bm25) (same intent: Science) - [What is Corpus Hub?](/science/corpus-hub) (same intent: Science) - [What is extractive answering?](/science/extractive-answering) (same intent: Science)