# Letta

Platform for stateful agents with advanced memory, personalization, and learning over time.

## Summary
Letta is an open-source platform for building stateful agents that remember users, maintain memory blocks, and interact through APIs and SDKs.


## Guide
Letta is an open-source platform for building stateful agents that remember users, maintain memory blocks, and interact through APIs and SDKs.

### What it is
Letta is an open AI memory systems resource tracked by OpenAgent.bot because it gives builders a concrete implementation path rather than just a product claim.

### Why it matters
Letta matters because memory is not just a database problem; it changes how an agent behaves over time. Letta gives builders a more structured model for stateful agents and persistent memory.

### How it works
Start from the official repository or documentation, verify the license and runtime requirements, then test it on a narrow workflow before expanding it into production use.


## Use Cases
- Personalized AI agents: Build assistants that retain a persona and user-specific memory blocks.
- Stateful agent APIs: Expose memory-backed agents inside applications through a service interface.
- Learning workflows: Experiment with agents that improve from ongoing interactions.

## Alternatives
- Choose Letta for stateful agent architecture vs standalone memory APIs: Letta is broader than memory storage; it is closer to a platform for agents whose behavior depends on state.

### Getting Started
- Review the GitHub repository: https://github.com/letta-ai/letta
- Read the documentation: https://docs.letta.com/
- Official source: https://www.letta.com/

### FAQ
- Is Letta open source?
  - Letta is listed with Apache-2.0 based on its official source links. Always re-check the repository or model card before production use.
- Who should evaluate Letta?
  - Developers building personalized stateful agents
## Why It Matters
Letta matters because memory is not just a database problem; it changes how an agent behaves over time. Letta gives builders a more structured model for stateful agents and persistent memory.


## Best For
- Developers building personalized stateful agents
- Teams that need memory APIs and SDKs instead of ad hoc context prompts
- Researchers exploring learning and self-improving agents

## Not For
- Users who want a fully managed consumer product with no setup work
- Teams that cannot review the linked source, license, and operational requirements before adoption

## What It Actually Does
- Stateful agent model: Letta treats memory as part of the agent state rather than a loose prompt append.
  - Why it matters: That makes it easier to build agents that remain coherent across sessions.
- API and SDK surface: Letta provides APIs and client SDKs for integrating stateful agents into applications.
  - Why it matters: Product teams need stable interfaces, not just demos.
- Active open-source platform: The project has frequent releases and documentation around agents and memory.
  - Why it matters: Active maintenance matters for infrastructure that sits inside an application.

## Typical Use Cases
- Personalized AI agents: Build assistants that retain a persona and user-specific memory blocks.
- Stateful agent APIs: Expose memory-backed agents inside applications through a service interface.
- Learning workflows: Experiment with agents that improve from ongoing interactions.

## How It Compares
- Choose Letta for stateful agent architecture vs standalone memory APIs: Letta is broader than memory storage; it is closer to a platform for agents whose behavior depends on state.

## Command Line
### Clone Letta
Use the official documentation for the current server, API, and SDK setup path.

```bash
git clone https://github.com/letta-ai/letta.git
```

## Facts
- Category: memory-systems
- Resource type: memory_system
- Open source: yes
- License: Apache-2.0
- Last verified: 2026-04-19
- GitHub repo: letta-ai/letta

## Capabilities
- memory
- state-management
- workflow-orchestration

## Structured Use Case Tags
- self-hosted-ai
- personal-memory

## Getting Started
- Review the GitHub repository: https://github.com/letta-ai/letta
- Read the documentation: https://docs.letta.com/
- Official source: https://www.letta.com/

## Links
- GitHub: https://github.com/letta-ai/letta
- Homepage: https://www.letta.com/
- Docs: https://docs.letta.com/

## Structured Outputs
- JSON: https://www.openagent.bot/memory-systems/letta.json
- Markdown: https://www.openagent.bot/memory-systems/letta.md
- Canonical: https://www.openagent.bot/memory-systems/letta