← Back to Glossary
Agent Memory (Short-Term)
Working memory held in the LLM context window during an active session (scratchpad and recent tool outputs).
Why it exists
Allows the agent to maintain continuity across reasoning turns and tool invocations within one run.
How it works
Appends tool calls, observations, and thoughts to the prompt messages array passed to the API.
Related terms
Where you'll use this
roadmap