Letta has developed the #1 open-source terminal-use agent, achieving a score of 42.5% on the Terminal-Bench, which evaluates AI agents on complex command-line tasks. Utilizing Letta's stateful agents SDK, the agent effectively manages context and memory, enabling it to outperform many proprietary models. This accomplishment highlights the importance of efficient memory management in enhancing the performance of AI agents in long-running tasks.