Skillget

letta

agent
Security Audit
Fail
Health Pass
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 6 days ago
  • Community trust — 23989 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in .github/workflows/alembic-validation.yml
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose

This tool is a platform and SDK for building stateful AI agents equipped with persistent memory that can learn and self-improve over time.

Security Assessment

Overall Risk: Medium. The platform allows agents to learn and self-improve, and explicitly helps users "do any task you can do on your computer," which implies high local system access and shell execution capabilities. It makes external network requests, primarily to fetch web pages and route API calls to third-party LLM providers. Authentication relies on user-provided API keys (e.g., `LETTA_API_KEY`) rather than hardcoded secrets. However, the automated rule-based scan failed due to a recursive force deletion command (`rm -rf`) found inside a GitHub Actions workflow file (`alembic-validation.yml`). While this is common in CI/CD pipelines for cleaning up directories, it should be visually verified by developers to ensure it is safely scoped and cannot be exploited via pipeline injection.

Quality Assessment

The project exhibits strong health and community trust. It is highly popular with over 22,000 GitHub stars, indicating widespread adoption and heavy community scrutiny. It is actively maintained, with the most recent code push occurring less than a month ago. Furthermore, it uses the standard Apache-2.0 license, which clearly grants permissions for commercial use, modification, and distribution without heavy legal restrictions. No dangerous runtime permissions were flagged during the scan.

Verdict

Use with caution: While the project is highly trusted, actively maintained, and safe to integrate via its SDK, its ability to autonomously execute terminal tasks locally demands strict sandboxing and oversight in production environments.
SUMMARY

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

README.md

Letta (formerly MemGPT)

Build AI with advanced memory that can learn and self-improve over time.

  • Letta Agent: run agents locally in your terminal, via the desktop app, or via channels like Slack
  • Letta Agent SDK: build agents into your applications

[!NOTE]
This repository contains the legacy Letta server (the API server behind the Letta V1 API and SDKs). Active development has moved to the Letta Agent repo, and self-hosting an API server is now done via the App Server. See AGENTS.md for details.

Get started in the CLI

Requires Node.js 22.19+

  1. Install the Letta Code CLI tool: npm install -g @letta-ai/letta-code
  2. Run letta in your terminal to launch an agent with memory running on your local computer

When running the CLI tool, your agent can help you code and do any task you can do on your computer.

Letta Code supports skills and subagents, and bundles pre-built skills/subagents for advanced memory and continual learning. Letta is fully model-agnostic, though we recommend the latest Anthropic, OpenAI, and zAI models for best performance (see our model leaderboard for our rankings).

Get started with the Letta Agent SDK

Use the Letta Agent SDK (TypeScript) to build stateful agents into your own applications.
The SDK can run agents on Constellation (Letta's agent cloud), fully locally on your machine, or against a self-hosted App Server.

Installation

npm install @letta-ai/letta-agent-sdk

Hello World example

Below is a quick example of creating a stateful agent and streaming a conversation with it (requires a Letta API key).
See the full quickstart guide for complete documentation.

import { LettaAgentClient } from "@letta-ai/letta-agent-sdk";

const client = new LettaAgentClient({
  backend: "cloud",
  apiKey: process.env.LETTA_API_KEY,
});

// Create your agent
const agentId = await client.createAgent({
  model: "anthropic/claude-opus-4-8",
  human:
    "Name: Timber. Status: dog. Occupation: building Letta, infrastructure to democratize self-improving superintelligence",
  persona:
    "I am a self-improving superintelligence. Timber is my best friend and collaborator.",
});

console.log("Agent created with ID:", agentId);

// Send your agent a message and stream the response
await using session = client.resumeSession(agentId);

await session.send("What do you know about me?");
for await (const message of session.stream()) {
  if (message.type === "assistant") console.log(message.content);
}

To run the same agent fully locally (the SDK spawns Letta Code on your machine as a subprocess), swap out the client:

const client = new LettaAgentClient({ backend: "local" });

Letta V1 SDK

The previous-generation V1 SDKs (@letta-ai/letta-client for TypeScript, letta-client for Python) target the Letta API directly and are still available (see the client SDKs). We recommend the Agent SDK for new projects.

Contributing

Letta is an open source project built by over a hundred contributors from around the world. There are many ways to get involved in the Letta OSS project!

Legal notices: By using Letta and related Letta services (such as the Letta endpoint or hosted service), you are agreeing to our privacy policy and terms of service.

Reviews (0)

No results found