Agentic Memory Systems
Architectures for managing different types of memory in AI agents — working memory for current tasks, episodic memory for past interactions, and semantic memory for accumulated knowledge.
Why It Matters
Memory systems transform agents from stateless assistants into persistent collaborators that build knowledge and improve over time.
Example
An agent with working memory (current conversation), episodic memory (past project interactions with this user), and semantic memory (accumulated domain knowledge across all users).
Think of it like...
Like the human memory system — short-term memory for what you are doing now, episodic memory for personal experiences, and semantic memory for general knowledge.
Related Terms
AI Memory
Systems that give AI models the ability to retain and recall information across conversations or sessions. Memory enables persistent context, user preferences, and accumulated knowledge.
Agent Memory
Systems that give AI agents persistent storage for facts, preferences, and conversation history across sessions. Memory enables agents to build cumulative knowledge over time.
AI Agent
An AI system that can autonomously plan, reason, and take actions to accomplish goals. Unlike simple chatbots, agents can use tools, make decisions, execute multi-step workflows, and adapt their approach based on results.
Context Management
Strategies for efficiently using an LLM's limited context window, including what information to include, how to compress it, and when to summarize or truncate.
Knowledge Base
A structured or semi-structured collection of information used by AI systems to retrieve factual data. In the context of RAG, it typically refers to the document collection that the system can search.