Letta Code

Letta Code is a memory-first coding agent built by the Letta team (creators of MemGPT and pioneers of LLM memory research). The pitch is direct: most coding agents work in independent sessions and lose all context when the conversation resets. Letta Code instead works with a persisted agent that remembers everything you've done, learns continuously from corrections and feedback, and stays portable across models — switch from Claude to GPT to an open-weight model without losing the agent's memory or skills. The harness includes MemFS (a virtual filesystem memory layer), Skills (reusable agent capabilities), Subagents for parallel work, and pluggable Providers so you can connect any model or coding plan. Headless mode and a CLI ship for terminal use, a desktop app for richer interactions, and remote/mobile access so you can check in on long-running agent work from your phone. A GitHub Action lets the same agent operate inside CI.

Key capabilities at a glance: Persisted agent memory across sessions; Model-portable: switch providers without losing memory; MemFS virtual filesystem memory layer; Skills, Subagents, and Hooks for extensibility; Desktop app, CLI, headless mode, GitHub Action; Letta Code SDK for building custom agents.

Where Letta Code wins: Persistent memory is genuinely different from every other coding agent in the category; Model portability is a real escape hatch from vendor lock-in; Free tier with BYOK means you can evaluate the entire harness without committing budget; Headless mode + GitHub Action means the same agent works in CI as on your laptop; Built by the MemGPT team — most credible memory research lineage in the space.

Trade-offs to weigh: Newer than Claude Code or Cursor; ecosystem of community Skills is still small; Memory layer adds operational complexity if you're used to ephemeral sessions; Letta Auto pricing isn't transparent on the public site at time of writing; Desktop app polish trails Cursor's; some workflows still require dropping to the CLI.

Best-fit scenarios include: Long-running coding projects where context matters; Multi-day research and refactoring tasks; Switching between models without losing agent state; Building custom memory-first agents on the Letta SDK.

Pricing structure: Free with BYOK (Free) — Use Letta Code free with your own OpenAI, Anthropic, OpenRouter, or compatible API keys. | Letta Auto (Paid (tiers on website)) — Bundled model usage with usage caps. | Teams (Custom) — Shared agents, collaboration, admin features.