Letta Code
Letta Code is a stateful agent harness for creating agents that are more like people than tools. Letta Code 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. Interact with agents through:
Feature Overview
[!TIP]
Letta Code agents are designed to be self-configuring. If you want to configure something (e.g. skills, behavior, hooks, permissions), try asking your agent to do it for you.
| Feature | Description |
|---|
| 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 |
| Message search | Search across all messages and agents with /search. Agent can also search their own conversations or the conversations of other agents |
| 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 |
| Permissions | Set permission modes and customize what actions are auto-approved or auto-denied |
| Crons & Schedules | Configure heartbeats and crons, and let agents work across time with self-managed schedules |
| Remote computers (requires signing in with Letta) | Agents work across multiple computers. Connect any machine by running letta server --computer-name "..." |
| Secrets (requires signing in with Letta) | Make secrets available as environment variables (across machines) while obfuscating their values from context |
Automatic client-side dreaming is disabled by default on native Windows, including when saved /sleeptime settings enable it. Manual /dream and /reflect commands remain available. To opt in, set LETTA_ENABLE_WINDOWS_AUTO_REFLECTION=1 in the environment of the Letta Code process. This does not affect macOS, Linux (including WSL), or server-side dreaming.
See the full list of slash commands in our documentation.
Get started
Install the package via npm:
npm install -g @letta-ai/letta-code
Alternatively, install with uv or pipx (Node.js is bundled):
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.
If npm install -g fails with EACCES, don't use sudo: root ownership prevents the CLI's npm install -g self-updates. Use uv/pipx, a user-owned npm prefix, or nvm. See the CLI installation docs.
Navigate to your project directory and run letta (see command-line options in the docs). 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; your choice is saved for future runs. 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 without changing the saved default.
Run /connect to configure your own LLM API keys (OpenAI / ChatGPT, Anthropic, Z.ai coding plan, etc.), and use /model to swap models.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
