Letta Code
Stateful agents that are like people, with memory, identity, and the ability to learn and adapt observed · 2026-10-21
Health v2 · maintenance only
81/100
- Activity 100
- Release rhythm 88
- Longevity 25
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-22. Adoption (stars, forks) is never an input.
- gap_med: 0
- age_days: 362
- days_rel: 1
- days_push: 1
- n_releases_24m: 350
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
5 sources
- readme: https://github.com/letta-ai/letta-code · fetched 2026-10-21 · 1d624e8fd383
- homepage: https://www.letta.com/agent · fetched 2026-09-28 · 219f7b5e10b0
- site_page: https://www.letta.com/about-us · fetched 2026-09-28 · 321781b099b4
- registry_npm: https://registry.npmjs.org/letta-code · fetched 2026-09-28 · bd223b9545e7
- site_page: https://www.letta.com/blog/sleep-time-compute · fetched 2026-09-28 · f0d0cc22f668
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| letta-ai/letta-code | main | 81 |
| letta-ai/letta | mirror | 83 |
| letta-ai/claude-subconscious | examples | 71 |
For agents
markdown · JSON · MCP: product_card(name="letta-ai/letta-code")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem