head to head · open source

claude-mem vs Letta

claude-mem has 110,572 GitHub stars, 9,645 forks, 186 open issues and last shipped yesterday. Letta has 3,764 stars, 465 forks, 347 open issues and last shipped yesterday. claude-mem leads on adoption by 2,838% (110,572 vs 3,764 stars). claude-mem is written in TypeScript under Apache-2.0; Letta is written in TypeScript under Apache-2.0. claude-mem has attracted 9% as many forks as stars, Letta 12%. Letta was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (ai, claude), so they are genuine substitutes rather than adjacent tools.

Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.

claude-mem ★ 111K Letta ★ 3.8K category AI & Machine Learning

← all 20902 open source comparisons

Side by side

claude-mem Letta
GitHub stars ★ 111K ★ 3.8K
License Apache-2.0 Apache-2.0
Written in TypeScript TypeScript
Last push 2026-11-02 2026-11-02
Forks ⑂ 9.6K ⑂ 465
Self-hosting Yes Yes
Data ownership Your server Your server

pick claude-mem if

  • You weight community size — 111K stars and counting
  • You want the Apache-2.0 license terms
  • Your stack matches TypeScript
  • You value the larger contributor base for long-term maintenance

full claude-mem profile →

pick Letta if

  • You want the Letta feature set and don't need the biggest community
  • You prefer the Apache-2.0 license terms
  • Your stack matches TypeScript
  • You evaluated both and Letta fits your workflow better

full Letta profile →

About claude-mem

Claude Mem is now Grok Mem. The package is still claude mem . 🇨🇳 中文 • 🇹🇼 繁體中文 • 🇯🇵 日本語 • 🇵🇹 Português • 🇧🇷 Português • 🇰🇷 한국어 • 🇪🇸 Español • 🇩🇪 Deutsch • 🇫🇷 Français • 🇮🇱 עברית • 🇸🇦 العربية • 🇷🇺 Русский • 🇵🇱 Polski • 🇨🇿 Čeština • 🇳🇱 Nederlands • 🇹🇷 Türkçe • 🇺🇦 Українська • 🇻🇳 Tiếng Việt • 🇵🇭 Tagalog • 🇮🇩 Indonesia • 🇹🇭 ไทย • 🇮🇳 हिन्दी • 🇧🇩 বাংলা • 🇵🇰 اردو • 🇷🇴 Română • 🇸🇪 Svenska • 🇮🇹 Italiano • 🇬🇷 Ελληνικά • 🇭🇺 Magyar • 🇫🇮 Suomi • 🇩🇰 Dansk • 🇳🇴 Norsk Grok Mem is how Grok Bots remember. Sits next to Grok's own memory. Does not replace it. Quick…

read the full claude-mem overview →

About Letta

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: A local CLI The desktop app for macOS, Windows, and Linux Your browser, including mobile, at chat.letta.com Messaging integrations, including Telegram, Slack, Discord, and…

read the full Letta overview →

More in AI & Machine Learning

Related comparisons

More AI Development Platforms projects

Compare either of these against the rest of the AI Development Platforms field.

Frequently asked questions

Is claude-mem or Letta more popular?

claude-mem has 110,572 GitHub stars and Letta has 3,764. claude-mem has the larger community by that measure.

Are claude-mem and Letta free?

Both are open source. claude-mem is licensed under Apache-2.0 and Letta under Apache-2.0. Neither carries a licence fee.

What is the difference between claude-mem and Letta?

claude-mem is written in TypeScript and Letta in TypeScript. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, claude-mem or Letta?

Choose claude-mem if you want the larger community (110,572 stars) or its Apache-2.0 licence terms. Choose Letta if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.