#266266th of 324 in Skills, plugins and prompts
nocturne_memory
Long-term memory MCP server with URI-addressed memories and a review dashboard
- Stars
- 1.4k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Aug 2026
- Language
- Python
862 on 3 Apr 20261,412 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Python MCP server (stdio, SSE, Streamable HTTP) that stores agent memories in SQLite or PostgreSQL as a URI-routed graph such as core://agent/identity. The agent gets 7 tools to create, update, alias, search and trigger-link memories, and a React dashboard lets the owner browse, diff and roll back every change. A system://boot entry loads configured core memories at session start.
Who it is for: Users giving MCP-based agents persistent memory across sessions and models
Strengths
- Works with any MCP client over stdio, SSE or Streamable HTTP, not tied to one LLM
- Every AI write creates a snapshot; dashboard offers diff, accept and rollback
- Runs on SQLite locally or PostgreSQL; namespaces isolate multiple agents in one database
- Public read-only demo server and dashboard available without installing
Weaknesses
- Search is full-text keyword only, not semantic
- Needs Python 3.10+ and Node.js; frontend builds on first start
- README is mostly Chinese and leans on persona and roleplay examples
- Docker setup starts from an empty PostgreSQL with no example data
What it needs
- no GPU
- Compose
- Needs Python 3.10+, Node.js, SQLite or PostgreSQL, Docker Compose (optional)
- Models: Any MCP client (Claude Code, Cursor, Gemini CLI, OpenAI Codex, Cline, etc.)
- port 8233
Quick answers
Is nocturne_memory open source?
Yes. Its code is on GitHub under the MIT license.
Can you run nocturne_memory with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |