Framework and cloud service for building stateful AI agents that remember, learn continuously, and improve over time — the successor to MemGPT.
Framework and cloud service for building stateful AI agents that remember, learn continuously, and improve over time — the successor to MemGPT.
Letta is the commercial evolution of MemGPT, the influential UC Berkeley research project that showed how LLM agents could operate with layered memory (short-term working memory, long-term archival memory, and self-editing 'core memory') to escape the context window and behave more like a persistent assistant. Letta packages that idea as both an open-source Python framework and a hosted platform. Developers define an agent with a persona, a memory model, and a set of tools, then let it converse with users indefinitely — Letta manages what belongs in the prompt versus what belongs in archival memory, and the agent can literally rewrite its own core memory as it learns.
The framework is model-agnostic and works with Anthropic, OpenAI, Google, Groq, Together, and any OpenAI-compatible endpoint. It ships with a REST API and SDKs for Python and TypeScript, an Agent Development Environment (ADE) for visualizing memory and step-by-step reasoning, and integrations for building tools with function calling. Letta supports Model Context Protocol both as a client (agents can call MCP servers as tools) and as a server (Letta agents can be exposed to other MCP-aware apps). The hosted plan handles infrastructure and provides a UI for creating and managing agents; the open-source framework can be self-hosted. It is the pick when you specifically need long-lived, self-editing memory rather than a stateless chat.
Was this helpful?
Letta (formerly MemGPT) offers a distinctive memory-first approach where agents manage persistent state instead of relying only on prompt reconstruction. The self-editing memory model is powerful for long-running assistants, but it is a developer-oriented platform with operational and evaluation complexity.
Three-tier memory: core memory that stays in context and can be edited by the agent, recall memory for searchable conversation history, and archival memory for long-term vector-style storage.
Use Case:
A personal assistant agent that keeps your current project details in core memory, recent conversations in recall, and years of interaction history in archival memory.
The agent has explicit tools for memory operations such as appending or replacing core memory, inserting archival memory, searching archival memory, and searching conversation history.
Use Case:
An agent that proactively archives important details from a meeting conversation and later retrieves them when the user asks about action items.
Agents run as persistent server-backed entities with REST API endpoints. State is maintained between API calls without requiring the client to rebuild full context on every request.
Use Case:
Deploying a fleet of customer-specific agents where each agent remembers its customer's history and preferences across months of interactions.
Visual interface for creating agents, defining core memory blocks, attaching tools, configuring LLM providers, and testing agent interactions before deploying through the API.
Use Case:
A product manager defining a new support agent's personality, knowledge base, and tools through a visual interface before handing it to engineering for production integration.
Agents can participate in multi-agent workflows where each agent maintains independent state and memory while collaborating through tool and message patterns.
Use Case:
A research agent that gathers information and sends summarized findings to an analysis agent, which then passes conclusions to a report-writing agent.
Agents can be equipped with custom tools and connected to external data sources that populate archival memory. Tools are defined for the agent to call during conversations or workflows.
Use Case:
Equipping a sales agent with CRM lookup tools and product database access that it searches autonomously when customers ask about pricing or features.
Free
Usage-based
Contact sales
Ready to get started with Letta?
View Pricing Options →Letta works with these platforms and services:
We believe in transparent reviews. Here's what Letta doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
Letta's current site highlights recent work including Context Constitution, Context Repositories for git-based memory in coding agents, Continual Learning improvements, Letta Code, Letta Auto, AgentFile portability, and expanded platform APIs for stateful agents.
AI Agents
Open-source Python framework for orchestrating role-playing, autonomous AI agents that collaborate as a 'crew' to complete complex tasks.
Multi-Agent Builders
Microsoft's open-source framework for building multi-agent AI systems with asynchronous, event-driven architecture.
AI agent framework
LangGraph is LangChain's open-source framework for building stateful, durable, multi-agent workflows in Python and JavaScript with graph-based control flow.
AI Agent Builders
SDK for integrating cutting-edge LLM technology into applications, with support for building AI agents and connecting model capabilities into existing app workflows.
No reviews yet. Be the first to share your experience!
Get started with Letta and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →AI agents without memory restart from zero every conversation, wasting time and money. Here's how the three types of agent memory work, why they matter for your business, and which tools actually deliver results in 2026.
The 10 trends reshaping the AI agent tooling landscape in 2026 — from MCP adoption to memory-native architectures, voice agents, and the cost optimization wave. With real tools leading each trend and current market data.
A hands-on comparison of the top AI agent frameworks — CrewAI, LangGraph, OpenAI Agents SDK, AutoGen, Google ADK, and more. Real code examples, setup times, and production guidance for builders.