Letta is an open-source platform for building stateful AI agents with persistent memory that learn and improve across sessions, created by the UC Berkeley MemGPT research team.

Overview

Letta (formerly MemGPT) is an open-source platform and managed cloud for building stateful AI agents — agents that keep persistent memory and improve during deployment, not just during training. Born from a UC Berkeley research paper, it gives an LLM an operating-system-like memory layer: a small core context, a searchable recall store, and a cold archival store, with the agent deciding what to promote or forget. Agents are exposed as REST APIs and SDKs (Python, TypeScript), run locally with no account, in the cloud, or on your own server. In 2026 the team shipped Letta Code, a memory-first coding agent ranked #1 among open model-agnostic agents on Terminal-Bench, and Channels for asynchronous agent messaging.

Key Features

  • Three-tier memory (core / recall / archival) so agents retain facts and preferences indefinitely
  • Model-agnostic: OpenAI, Anthropic, Mistral, or local models with state preserved across swaps
  • Agent Development Environment to visualize memory, reasoning steps, and tool calls live
  • REST API + Python/TypeScript SDKs; self-host (Apache 2.0) or managed Letta Cloud
  • Letta Code desktop agent and Channels for async, multi-agent messaging

Pricing

PlanPriceFor
Free$0Up to 3 managed agents, bring-your-own-key, self-host
Pro$20/moUp to 20 stateful agents plus Letta Auto model quota
EnterpriseCustomHigher scale, SSO, dedicated support, compliance

Comparison

Compared to LangChain, Letta centers on persistent memory and state rather than chaining tools, which matters once an agent must recall context weeks later. Compared to AutoGPT, Letta adds a production-grade memory store and a visual debugging environment instead of a bare autonomous loop.

Compare alternatives

Side-by-side with the 3 closest alternatives.

ToolCategoryPricingVisit
Letta (this) codeFree $0 · From $20/mo Site ↗
LangChaincode, agentsFrom $0/mo Site ↗
Difyagents, productivityFrom $0/mo Site ↗
AutoGPTagentsFrom $0/mo Site ↗
Letta Current

Letta is an open-source platform for building stateful AI agents with persistent memory that learn and improve across sessions, created by the UC Berkeley MemGPT research team.

code
Free $0 · From $20/mo

The most-adopted open-source framework for building LLM apps and agents, plus the LangSmith platform for tracing and deployment.

codeagents
From $0/mo

Open-source LLM app and agent platform with a visual workflow canvas, RAG pipelines, and one-click cloud or self-hosted deployment.

agentsproductivity
From $0/mo

Open-source platform for building and running autonomous AI agents. Pioneered autonomous agents Read our hands-on review and compare the top AI Agents

agents
From $0/mo
Editor’s Review
4.5/5
Pros
  • +Persistent three-tier memory lets agents actually learn across sessions, not just per call
  • +Model-agnostic: swap OpenAI, Anthropic, Mistral, or local models without losing state
  • +Open source (Apache 2.0) with a managed cloud and a visual Agent Development Environment
Cons
  • Self-hosting and memory tuning add real ops overhead for small teams
  • Smaller ecosystem and fewer prebuilt connectors than LangChain
  • Stateful memory can surprise you if guardrails on what gets stored are weak

Letta solves the problem most agent frameworks ignore — what the agent remembers after the conversation ends. If your use case needs continuity (support bots, personal assistants, long-running workflows), its memory architecture is genuinely better than stateless orchestrators. For one-shot scripting, it is heavier than you need.

See all reviews →