Letta is an AI research lab in San Francisco building machines that learn. We envision a future where humans coexist with digital people: experiential agents that remember everything, learn continuously, …

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time. - letta-ai/letta

Letta is founded by PhD researchers out of UC Berkeley that have charted the frontier of memory and continual learning in the modern LLM era, including MemGPT (agentic context management), …

Letta is an AI lab building machines that learn. Letta has 49 repositories available. Follow their code on GitHub.

Building machines that learn. Try Letta Code: the memory-first agent.

Letta | 5,700 followers on LinkedIn. The platform for building stateful agents | Today's AI agents struggle with fragmented context and limited memory. Just as computers needed operating systems ...

Sep 23, 2024 · AI memory management startup Letta just emerged from stealth with $10 million in seed led by Felicis and a bunch of big-name angels.

Oct 4, 2024 · What’s Letta ai? A complete guide Letta AI is an advanced platform designed for developers who want to build “stateful” applications using Large Language Models (LLMs).

Letta was born in Pisa, Tuscany, to Giorgio Letta, an Abruzzo -born professor of mathematics who taught probability theory at the University of Pisa, member of the Lincean Academy and of the …

Jun 9, 2026 · Letta (formerly MemGPT) is an open-source platform for building stateful AI agents with persistent memory, originally developed as a research project at UC Berkeley's Sky Computing Lab. …