letta-code

Agents that self-improve with experience

What is letta-code?

Agents that self-improve with experience

Overview of letta-code

What it is

Letta Code is a stateful agent harness for creating agents that are more like people than tools. Agents have memory, identity, and a sense of experience over time. They learn and evolve over long horizons through rewriting their own memory, skills, prompts, and even the harness itself (through mods). Letta Code can be used interactively or to power always-on agents that work proactively. Interaction methods include a local CLI, a browser (chat.letta.com), and messaging integrations such as Telegram, Slack, Discord, and custom channels.

Key features

  • Self-improvement & Learning: Agents programmatically rewrite their context to improve and adapt over time, including system prompt learning (through memory blocks) and skill learning. Configure periodic dreaming with /sleeptime, investigate agent behavior with /doctor [symptom], and view memory with /palace.
  • MemFS: All context (including memory blocks) is tracked via git. Sync context to a custom GitHub repository by setting /memory-repository set [email protected]:....
  • Skills: Loads global skills (~/.letta), project-scoped skills (.agents/skills), and agent-scoped skills (stored in MemFS). View skills with /skills and create with /skill-creator.
  • Subagents & Multi-agent: Call built-in subagents (general-purpose, forked, recall) in the background. Agents can call any other agent (including themselves) as subagents.
  • Messaging Integrations: Chat with the same agent from Slack, Telegram, your browser (chat.letta.com) including mobile, and through custom channels.
  • Hooks: Run custom scripts at key points of agent execution to automate workflows.
  • Remote computers (requires signing in with Letta): Agents work across multiple computers. Connect any machine by running letta server --computer-name ....

Use cases

Letta Code is designed for creating agents that learn and adapt over time. Use cases include interactive chat via CLI or browser, always-on agents that work proactively across messaging platforms, agents that manage their own memory and skills, multi-agent systems where agents call each other as subagents, and agents that operate across multiple remote computers. The project is driven by research in AI memory and continual learning, developed by the creators of MemGPT and sleep-time compute (dreaming).

Getting started

Install the package via npm: bash npm install -g @letta-ai/letta-code Alternatively, install with uv or pipx (Node.js is bundled): bash uv tool install letta # or pipx install letta Requires Python 3.9+. Wheels support glibc Linux 2.28+ (x86-64/ARM64), macOS 14+ (Intel/Apple Silicon), and Windows x64; Alpine/musl, 32-bit systems, and Windows ARM64 are unsupported. Navigate to your project directory and run letta. You can also run the tutorial agent with: letta --new-agent --personality tutorial Letta Cloud is the default. On first launch, choose to sign in with Letta or proceed locally. Run letta setup to choose again, or letta backend cloud / letta backend local to change the default. Use --backend cloud or --backend local for a one-off override. Run /connect to configure your own LLM API keys and /model to swap models.

License and pricing

The license is Apache-2.0. The project is open source and free to use.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/letta-ailetta-code.svg)](https://yunodb.com/tools/letta-ailetta-code?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/letta-ailetta-code?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/letta-ailetta-code.svg" alt="Featured on YunoDB" height="20"></a>