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.
The Four Types of Memory Unlike standard apps, Agents need memory modeled somewhat like a human brain: Working Memory: The current LLM context window....
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...
Choosing and Using Vector Databases Vector databases are the backbone of agent long-term memory. They store embeddings (numerical representations of t...
Keeping Agents Fast and Cheap Without caching and compaction, agent costs grow linearly with conversation length. A 50-turn conversation can cost 100x...