Letta is an AI research lab based in San Francisco focused on building stateful AI agents with persistent memory. The company's work centres on enabling agents to continuously learn and improve from their own experience, with core technical domains spanning AI agents, persistent memory, continual learning, and memory management.
The company's main product, Letta Code, is a model-agnostic agent framework that provides persistent memory, computer use capabilities, skills, subagents, and deployment paths for language models. The platform is designed to work across different underlying models rather than being tied to a single provider.
Letta emphasises transparency and user ownership in its approach. Developers using the platform can inspect how their agents operate at the token level, providing visibility into agent behaviour and decision-making processes.
