#1212th of 12 in Memory

Letta

Stateful agent harness with git-tracked memory, channels and remote computers

Stars
3.6k
License
Apache-2.0
Last commit
Oct 2026
Last release
Oct 2026

Overview

Letta Code is an npm-installed agent harness whose agents keep memory blocks, skills and prompts in a git-tracked MemFS and rewrite them over time. Agents run from a CLI, desktop app, browser (chat.letta.com) or Telegram, Slack and Discord channels, use subagents, hooks and cron schedules, and can run on remote machines via letta server. Letta Cloud is the default backend; local is available.

Who it is for: Developers who want agents that keep learning across sessions and devices

Strengths

  • All agent context including memory blocks is versioned in git (MemFS)
  • Same agent reachable from CLI, desktop, browser, Telegram, Slack and Discord
  • Skills installable from GitHub, ClawHub or the Hermes Skills Hub
  • Apache-2.0; Nix flake and AUR packages available

Weaknesses

  • Letta Cloud is the default; remote computers and secrets require signing in
  • Self-hosted app server setup is not described in the README; local backend only mentioned
  • AgentFile export/import removed; agent registry imports no longer supported
  • Automatic dreaming is disabled on native Windows by default

What it needs

  • no GPU
  • Docker
  • Models: OpenAI / ChatGPT, Anthropic, Z.ai coding plan

Also in Memory

See all 12
Also in Memory
RankProjectScore
1hindsightAgent memory server with retain, recall and reflect operations48k stars, MIT78 out of 100
2MemPalaceLocal verbatim memory for coding agents on ChromaDB with 45 MCP tools59.5k stars, MIT77 out of 100
3agentmemoryPersistent memory server for coding agents, exposed over MCP and REST29.3k stars, Apache-2.075 out of 100
#4OpenVikingContext database exposing agent memory, knowledge and skills as a filesystem Live demo ↗ (opens in a new tab)39.6k stars, AGPL-3.074 out of 100
#5Mem0Memory layer for agents with a self-hosted server, SDKs and CLI Live demo ↗ (opens in a new tab)67k stars, Apache-2.073 out of 100