Letta
letta.com · 131 words · saved by 2 readers
Making machines that learn. Create stateful agents that remember everything, learn continuously, and improve themselves over time.
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, and improve themselves over time. $ npm i -g @letta-ai/letta-code Our research ships as software: Letta Agent, a self-improving AI agent whose memory, identity, and capabilities evolve with experience. Featured case studies: Bilt, 11x, Kognitos, Hunt Club. Founded by the creators of MemGPT from UC Berkeley’s Sky Computing Lab, the birthplace of Spark and Ray. Advised by Ion Stoica and…
saved by
related reading
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Works - Ran Liranli.me
- Together AI | The AI Native Cloudtogether.ai
- Ai2: Truly open breakthrough AIallenai.org
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- Trending Papers - Hugging Facepaperswithcode.com
- GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automaticallygithub.com
- General Intelligence Companygeneralintelligencecompany.com
- LangChain: the open agent platform to own your intelligencelangchain.com
- Stanford CS329A | Self-Improving AI Agentscs329a.stanford.edu
- Hermes Agent — The Agent That Grows With Youhermes-agent.nousresearch.com
- Building reliable AI agents · parth sareenparthsareen.com