Letta
Platform for stateful agents with memory, identity and the ability to learn over time (formerly MemGPT); terminal UI, App Server, desktop app and Agent SDK.
Tags
Description
Current source lives in letta-ai/letta-code, now called the Letta Harness (formerly Letta Code; npm @letta-ai/letta-code), with a git-versioned memory filesystem (MemFS), skills, schedules and sleep-time subagents. The original letta-ai/letta repo (not archived) points there and keeps the retired V1 API server on an archive branch.
Agent access
Related
- Mem0: Memory layer for AI agents and apps: drop-in persistent memory that lets agents learn from past interactions.
- Hosted Letta MCP Server: Hosted MCP server that lets any MCP client create stateful Letta agents, delegate work to them and read their replies.
Guides & comparisons
- Give an agent long-term memory (Guide): How to make an agent remember users, facts and lessons across sessions, choosing between file-based memory, a memory layer such as Mem0, a temporal knowledge graph such as Zep or Graphiti, a stateful agent platform such as Letta, or your own store.
- Memory layers for AI agents (Comparison): Mem0, LangMem, the Claude memory tool, Graphiti, Zep, Cognee, Letta and SurrealDB Agent Memory compared on memory model, who writes memories, self-hosting and license, hosted pricing, MCP servers, SDK languages and framework ties.
- Research memory libraries compared: A-MEM vs MemoryOS vs MemOS vs LightRAG (Comparison): Four open-source memory systems that started as research papers. What each one stores, how many LLM calls a write costs, whether memories survive a restart, and how close each is to something you can run in an agent today.
- Memory servers for coding agents compared: m3 Memory vs agentmemory vs Basic Memory vs MCP Memory Service (Comparison): Four self-hosted memory servers that give Claude Code, Codex, Cursor and other MCP clients one shared memory across sessions and tools. Covers install, storage, search, how memories get captured, hosted options and license.
Sources
- https://github.com/letta-ai/letta
- https://github.com/letta-ai/letta-code
- https://docs.letta.com/
- https://docs.letta.com/llms.txt
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)