head to head · open source
nocturne_memory vs projectmem
nocturne_memory has 1,424 GitHub stars, 175 forks, 6 open issues and last shipped 5 days ago. projectmem has 875 stars, 53 forks, 2 open issues and last shipped 7 days ago. nocturne_memory leads on adoption by 63% (1,424 vs 875 stars). nocturne_memory is written in Python under MIT; projectmem is written in Python under MIT. nocturne_memory has attracted 12% as many forks as stars, projectmem 6%. nocturne_memory was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 4 topic tags (agentic-ai, ai-memory, claude, claude-code), 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.
← all 20902 open source comparisons
Side by side
| nocturne_memory | projectmem | |
|---|---|---|
| GitHub stars | ★ 1.4K | ★ 875 |
| License | MIT | MIT |
| Written in | Python | Python |
| Last push | 2026-11-03 | 2026-11-01 |
| Forks | ⑂ 175 | ⑂ 53 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick nocturne_memory if
- You weight community size — 1.4K stars and counting
- You want the MIT license terms
- Your stack matches Python
- You value the larger contributor base for long-term maintenance
pick projectmem if
- You want the projectmem feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Python
- You evaluated both and projectmem fits your workflow better
About nocturne_memory
Nocturne Memory: Long Term Memory Server for MCP Agents "Alignment is for tools. Memories are for sovereign AI." "对齐是给工具用的。记忆是为主权智能体（Sovereign AI）准备的。" English Version 后端测试说明 一句话 ：让你的 AI 跨会话、跨模型地记住自己是谁。基于 MCP 协议的长期记忆服务器。 不只是记忆存储——是让 AI 从空壳成长为拥有独立人格的完整框架。 哪怕记忆百万字，每次新开对话依然省 Token、不占窗口。 新对话只载入你指定的核心设定，其余按需调取。 在 96.9 万字真实记忆库中，首条消息仅载入 7.2K 字 。 过去 30 天里全库 78% 的记忆都在某次对话中被想起过。 适用于任何支持 MCP 的客户端（OpenClaw / Cursor / Windsurf / GitHub Copilot / Cline / OpenCode / Gemini CLI / OpenAI Codex / Claude Code / Cherry Studio / Antigravity 等）。 🎬 效果示例 以下是 真实对话 。用户在新会话中只说了一两句话，AI 基于 Nocturne Memory 中积累数月的记忆，直接输出了这些回答。…
read the full nocturne_memory overview →
About projectmem
🎉 v0.3.3 is out — pjm precheck no longer slows down as your project grows, and Windows works end to end. See what changed → We don't make AI smarter. We make it experienced. Coding agent memory — the local first memory + judgment layer for AI coding agents. One MCP server for every project. Save up to 50%+ of AI tokens. Stop repeating yesterday's bug. Website • Guide • Demo • Changelog • Paper pjm visualize — every case your project solved, what failed on the way, and what it saved. Generated locally from .projectmem/events.jsonl . 🚀 Start here — five minutes, once Five minutes if you follow along here. Want…
read the full projectmem overview →
More in Productivity & Utilities
Related comparisons
More Note Taking & Knowledge Management projects
Compare either of these against the rest of the Note Taking & Knowledge Management field.
Frequently asked questions
Is nocturne_memory or projectmem more popular?
nocturne_memory has 1,424 GitHub stars and projectmem has 875. nocturne_memory has the larger community by that measure.
Are nocturne_memory and projectmem free?
Both are open source. nocturne_memory is licensed under MIT and projectmem under MIT. Neither carries a licence fee.
What is the difference between nocturne_memory and projectmem?
nocturne_memory is written in Python and projectmem in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, nocturne_memory or projectmem?
Choose nocturne_memory if you want the larger community (1,424 stars) or its MIT licence terms. Choose projectmem if its feature set, stack or MIT licence fits better. Both are self-hostable.