Letta Code: Memory-First Coding Agent with Continual Learning

Agent Agentic AI Continual Learning Memory Skills

Letta Code is a memory-first coding agent that improves with use, unlike traditional coding agents which operate in independent sessions. It utilizes long-lived agents that persist across sessions and learn from experience through agentic context engineering, long-term memory, and skill learning. The more you work with a Letta Code agent, the better it becomes as it accumulates context and memory.

Memory Initialization is facilitated through the `/init` command, which encourages the agent to learn about an existing project by running deep research on the local codebase, forming memories, and rewriting its system prompt as it learns. The agent continues to learn automatically, but you can also explicitly trigger it to reflect and learn with the `/remember` command.

Skill Learning is a key feature of Letta Code, allowing agents to learn from complex tasks and then reference these skills for similar tasks in the future. This can significantly improve performance on future similar tasks. Skills are stored as .md files, which can be managed in git repositories for versioning and used by other coding agents that support skills. Letta Code also supports the Letta Developer Platform and can be used with a self-hosted Letta server.

Additionally, Letta Code is the #1 model-agnostic OSS harness on TerminalBench, achieving comparable performance to harnesses built by LLM providers on their own models. It can be installed with npm or from source, and is designed to work just as well with a frontier model as it would with a specific harness built by the model provider.

Letta Code: A Memory-First Coding Agent

Letta Code is a memory-first coding agent, designed for working with agents that learn over time. When working with coding agents today, interactions happen in independent sessions. Letta Code is built around long-lived agents that persist across sessions and improve with use. Rather than working in independent sessions, each session is tied to a persisted agent that learns. Letta Code is also the #1 model-agnostic OSS harness on TerminalBench, and achieves comparable performance to harnesses built by LLM providers (Claude Code, Gemini CLI, Codex CLI) on their own models.

Continual Learning & Memory for Coding Agents

Agents today accumulate valuable experience: they receive the user’s preferences and feedback, review significant parts of code, and observe the outcomes of taking actions like running scripts or commands. Yet today this experience is largely wasted. Letta agents learn from experience through:

  • Agentic context engineering
  • Long-term memory
  • Skill learning

The more you work with an agent, the more context and memory it accumulates, and the better it becomes.

Memory Initialization

When you get started with Letta Code, you can run an /init command to encourage your agent to learn about your existing project. This will trigger your agent to run deep research on your local codebase, forming memories and rewriting its system prompt (through memory blocks) as it learns.

Your agent will continue to learn automatically, but you can also explicitly trigger your agent to reflect and learn with the /remember command.

Skill Learning

Many tasks that we work on with coding agents are repeated or follow similar patterns - for example API patterns or running DB migrations. Once you’ve worked with an agent to coach it through a complex task, you can trigger it to learn a skill from its experience, so the agent itself or other agents can reference the skill for similar tasks in the future.

Skill learning can dramatically improve performance on future similar tasks, as we showed with recent results on TerminalBench.

On our team, some skills that agents have contributed (with the help of human engineers) are:

  • Generating DB migrations on schema changes
  • Creating PostHog dashboards with the PostHog CLI
  • Best practices for API changes

Since skills are simply .md files, they can be managed in git repositories for versioning - or even used by other coding agents that support skills.

Persisted State

Agents can also lookup past conversations (or even conversations of other agents) through the Letta API. The builtin /search command allows you to easily search through messages, so you can find the agent you worked on something with. The Letta API supports vector, full-text, and hybrid search over messages and available tools.

Letta Code is the #1 model-agnostic OSS coding harness

Letta Code adds statefulness and learning to coding agents, but is the #1 model-agnostic, OSS harness on Terminal-Bench. Letta Code’s performance is comparable to provider-specific harnesses (Gemini CLI, Claude Code, Codex) across model providers, and significantly outperforms the previous leading model-agnostic harness, Terminus 2.

This means that even without memory, you can expect Letta Code agents to work just as well with a frontier model as they would with a specific harness built by the model provider.

Getting Started with Letta Code

To try out Letta Code, you can install it with:

npm install -g @letta-ai/letta-code

Or install from source (see the full documentation).

Letta Code can be used with the Letta Developer Platform, or with a self-hosted Letta server.

Company Announcements, Partnerships

Product: Release Notes, Feature Announcements

Research: Sleep-time Compute, Anatomy of a Context Window

This is some text inside of a div block.

Read original article

Related Articles

Taskmaster AI: Managing Your AI Workforce

Product Announcements • AI, Agent, PM, TaskManager, Tools

Building an Agent with Tool Access: A Practical Guide

Tools, specifically "Agent Developer Tools • Agent, Anthropic, Claude, Code, Coding

Manage Multiple Claude Code Agents with Conductor Software

News & Updates • Agent, Automation, Code, Git, Workflow