Agent Memory
Manage context windows, state persistence, and long-term recall. Part of the free AI Agents Academy — every lesson below is open to everyone, no signup required.
// LESSONS IN THIS MODULE
- 01Memory Architecture10 min · 80 XP
The Four Types of Memory Unlike standard apps, Agents need memory modeled somewhat like a human brain: Working Memory: The current LLM context window....
- 02Context Window Management12 min · 90 XP
Surviving Long Horizons Even with 1-million token context windows, an agent running for hours will run out of space or suffer from the "Lost in the Mi...
- 03Vector Databases Deep Dive10 min · 80 XP
Choosing and Using Vector Databases Vector databases are the backbone of agent long-term memory. They store embeddings (numerical representations of t...
- 04Caching & Conversation Compaction10 min · 90 XP
Keeping Agents Fast and Cheap Without caching and compaction, agent costs grow linearly with conversation length. A 50-turn conversation can cost 100x...