Letta Code

Health v2 · maintenance only

Adoption not part of the score

3669 stars · 440 forks observed · 2026-10-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-12, confidence 0.96

Letta is a platform for building stateful AI agents with persistent memory that can learn and improve over time. It provides a CLI, server, desktop app, and SDK for integrating agents into TypeScript applications.

Use cases

• Create AI assistants that remember past interactions and adapt their behavior.
• Run autonomous agents that perform scheduled tasks and learn from outcomes.
• Integrate custom LLM agents into Slack, Discord, or Telegram for team collaboration.
• Develop self‑improving bots that use sleep‑time compute to refine their knowledge.
• Deploy persistent agents across multiple devices with shared memory.

When to choose

• You need an AI agent with long‑term memory that can evolve without retraining the model.
• You want a unified CLI and server for developing, testing, and hosting stateful agents.
• Your workflow involves integrating agents into existing TypeScript or JavaScript projects.
• You require multi‑model support and the ability to run agents on local or cloud infrastructure.

When to avoid

• You only need a stateless LLM call without persistent context.
• Your project is not based on Node.js or does not support the required runtime.
• You require a fully managed cloud service with no self‑hosting responsibilities.

Facets

application · maturity active

cli http-server api-framework llm-inference agent-framework artificial-intelligence large-language-models cli stateful-agents persistent-memory continual-learning sleep-time-compute multi-model-memory ai-agents retrieval-augmented-generation nodejs desktop web-server docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="letta-ai/letta-code")