ActiveDeveloperOpen Source, Apache-2.0
Letta (MemGPT)
Platform for stateful agents
Letta, formerly MemGPT, is a platform for building stateful AI agents that can remember, learn continuously, and self-improve over time. It solves the AI memory problem through advanced memory management (MemGPT architecture). The platform offers both a CLI tool (Letta Code) for running agents locally and an API (Letta API) for integration into applications.
Good fit if
Focus: Developers and ML engineers who want to build stateful AI agents with persistent memory.
- your project is about Long-term memory for AI agents, Persistent conversational agents or Stateful multi-agent systems
- someone on your team writes code
Probably not if
- nobody on your team writes code (1/5 for use without developers)
- your team is just getting started with agents (skill level: Advanced)
Key figures
- Usable without developers
- 1/5
- Scalability
- 5/5
- Integrations
- 5/5
- Versioning
- 4/5
- Observability
- 3/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Platform for stateful agents
- Licence
- Open Source (Apache-2.0)
- Pricing
- FreemiumLetta Code (CLI tool) is open source and free. The Letta API requires an API key, and Pro and Enterprise plans are offered for production deployments.
- Deployment
- Cloud, Self-Hosted
- Models
- OpenAI, Anthropic
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO no, RBAC no
- Latest version
- 0.34.9
- GitHub stars
- 25,100
Key features
- Agents with memory and learning capabilities
- Model-agnostic
- Virtual Context
- Memory management (MemGPT architecture)
- Context Repositories (Git-based memory)
Typical use cases
- Long-term memory for AI agents
- Persistent conversational agents
- Stateful multi-agent systems
Implementation
Get Letta (MemGPT) implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperAutoGenAutoGen is an open-source framework from Microsoft Research for multi-agent systems, known for group chats between agents and code execution. With the release of Microsoft Agent Framework 1.0 in April 2026, AutoGen entered maintenance mode: it only receives bug fixes and security updates, and new development happens in Agent Framework. Microsoft recommends Agent Framework for new projects.View profile
- DeveloperElizaOSElizaOS is an open-source TypeScript framework for autonomous agents with personality, memory and plugins. Agents can connect to Discord, X, Telegram and other platforms, and more than 200 plugins extend their capabilities up to blockchain applications. Multiple agents can collaborate through a shared message bus.View profile
- DeveloperLlamaIndexLlamaIndex is a framework for LLM applications that work with your own data, especially RAG and document agents. It offers ingestion connectors, index structures, query engines and, with Workflows, an event-driven model for multi-step agents. LlamaCloud with LlamaParse adds document processing as a commercial service.View profile
- DeveloperMastraMastra is a comprehensive framework for building AI-powered applications and agents with a modern TypeScript stack. It provides all the necessary tools to go from early prototypes to production-ready applications. Mastra integrates with frontend and backend frameworks like React, Next.js, and Node, or can be deployed as a standalone server. It is designed to build, tune, and scale reliable AI products.View profile