Light
Dark
left click to zoom
LLM Agents
LLM Agents
LLM Agents
LLM Agents
LLM Agents

Advancing the frontier of AI systems with memory

Request early accessDeveloper docs
Products

Hosted Cloud

Get started

Create, deploy, and manage your agents at scale with Letta Cloud. Build production applications backed by agent microservices with REST APIs.

Letta API

View docs

Letta adds memory to your LLM services to give them advanced reasoning capabilities and transparent long-term memory (powered by MemGPT).

Backed by research from
PLAY

Build AI agents and persist them in a database. Create agent microservices. With Letta’s popular agents framework, powered by MemGPT’s memory management technique, you can create and deploy useful agents that actually last.

Top priority: memory management

We believe that programming agents starts with programming memory. Built by the researchers behind MemGPT, introducing self-managed memory for LLMs.

Read the research

The future of agent development starts here

Expose the entire sequence of tool calls, reasoning, and decisions that explain agent outputs, right from Letta's Agent Development Environment (ADE).

Book a demo

Build beyond the prototype

Most systems are built on frameworks that stop at prototyping. Letta's Cloud is built by systems engineers for production at scale so the agents you create can increase in utility over time.

Run the server

The box is white

Interrogate the system, debug your agents, and fine-tune their outputs, all without succumbing to black box services built by Closed AI megacorps.

Open Source

Our AI systems are model agnostic

Bring-your-own LLMs and RAG system. Pick the model providers that work for your use case, swap them at will. Control is yours.

Supported models
GitHub
Contribute to the Letta open source
Visit our GitHub
Documentation
Learn how to use the Letta AI platform
Read our docs
Discord
Join our developer Discord community
Join our Discord

About the company

Born out of the Sky Computing Lab at UC Berkeley, Letta believes that programming agents starts with programming memory.

Read more

We're hiring! Will you join us?

Build the next generation of agentic systems
Our values
Open AI and model freedom
Power to the developers
Nimble, talent-dense teams
Flat structure & high trust
We
in-person work
We offer
Top tier medical coverage
Competitive salary & equity
Workstation stipend
Office located in the heart of SF
Additional benefits
See open positions

Latest news

No items found.
Sep 23, 2024

Announcing Letta

We are excited to publicly announce Letta.

No items found.
Sep 23, 2024

MemGPT is now part of Letta

The MemGPT open source project is now part of Letta.

Around the web

Press
Understanding memGPT: Enhancing Conversational AI through Memory Augmentation

Conversational AI has witnessed remarkable advancements with models like GPT, which excel in generating human-like text. However, a critical limitation of these models, including ChatGPT, lies in their inability to maintain coherent dialogue across extended conversations. Contextual retention and coherence degradation hinder the seamless flow of conversation, leading to disjointed interactions.

Press
MemGPT Giving AI Unlimited Prompt Size (Big Step Towards AGI?)

In this video, we look at MemGPT, a new way to give AI unlimited memory/context windows, breaking the limitation of highly restrictive context sizes. We first review the research paper, then I show you how to install MemGPT, and then we have special guests!

Press
MemGPT with Real-life Example: Bridging the Gap Between AI and OS

In this tutorial, we discuss and show how to run MemGPT - an LLM with the potential for infinite context understanding.

Press
MemGPT: Unlimited Memory without Token Constraints for Generation

MemGPT, standing for Memory-GPT, is a system devised to enhance the performance of Large Language Models (LLMs) by introducing a more advanced memory management scheme, helping to overcome the challenges posed by fixed context windows. Below are some of the key features of MemGPT: