nocturne_memory
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
No outside reports on file
This tool creates a new data store that agents trust completely; secure it like you would a production database, verify what gets stored, and monitor access closely.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (Dataojitori/nocturne_memory)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/Dataojitori/nocturne_memory ↗
About Nocturne Memory
Nocturne Memory is an MCP server that gives AI agents a persistent memory system using graph-like structures instead of vector databases. It lets agents remember information across conversations and sessions, with the ability to roll back changes if needed.
Who it’s for
Developers building AI agents that need long-term memory and context persistence. Teams looking to replace vector RAG (retrieval-augmented generation) systems with a lighter-weight alternative.
Alternatives
- LangGraph persistence (LangChain's built-in memory and state management)
- Mem0 (AI memory platform with structured recall)
- ChromaDB (lightweight vector database for RAG workflows)
- AgentMemory (custom memory systems built on standard databases like PostgreSQL)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/Dataojitori/nocturne_memory (opens external site) for installation and configuration instructions specific to your setup.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.4k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Memory access: The server stores all agent memories in a local database; if compromised, an attacker gains access to everything the agent has learned
- Injection attacks: Malicious data fed into memory could corrupt the graph structure or trick the agent into false beliefs
- Data leakage: Sensitive information (credentials, API keys, user data) stored in memory could be exposed if the database is accessed
- Rollback abuse: An attacker who controls the server could roll back memory to erase evidence or revert security-relevant decisions
- No built-in encryption: The project description does not mention encryption at rest, so memory may be stored in plain text
How to lower the risk
Least-privilege permissions
- Run the server with minimal file system and network permissions
- Restrict which AI models and tools can write to or read from memory
Network isolation
- Keep the memory server on a private network, not exposed to the internet
- Use authentication tokens if the server accepts remote connections
Monitoring
- Log all memory read and write operations to detect tampering
- Alert if memory grows unexpectedly or contains suspicious patterns
Red flags to watch for
- Memory entries that contradict your agent's training or policies
- Sudden rollbacks without explanation or audit trail
- Sensitive data (passwords, keys, personal info) appearing in stored memories
Questions
How do I install Nocturne Memory?
Nocturne Memory does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/Dataojitori/nocturne_memory.
Are there security reports about Nocturne Memory?
No reports found for this package in our research (last checked 2026-10-29). Nocturne Memory currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include memory access, injection attacks, data leakage.
Is Nocturne Memory actively maintained?
Nocturne Memory has 1.4k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/Dataojitori/nocturne_memory before pinning it in production.
What are alternatives to Nocturne Memory?
Notable alternatives to Nocturne Memory include LangGraph persistence, Mem0, ChromaDB, AgentMemory. You can also compare Nocturne Memory side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Nocturne Memory? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/dataojitori-nocturne-memory)HTML embed:
<a href="https://agentarmorhq.com/skills/dataojitori-nocturne-memory"><img src="https://agentarmorhq.com/api/badge/dataojitori-nocturne-memory" alt="AgentArmorHQ Risk Grade for Nocturne Memory" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "dataojitori-nocturne-memory"Share with your security lead
Need sign-off to use nocturne_memory? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: nocturne_memory
- **Listing URL:** https://agentarmorhq.com/skills/dataojitori-nocturne-memory
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.4k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (Dataojitori/nocturne_memory)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/Dataojitori/nocturne_memory
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- Dataojitori
- Source code
- github.com/Dataojitori/nocturne_memory
- Est. context load
- ~900 tokens / turn (~5 tool schemas, 0.45% of 200k context)
- Popularity
- 1.4k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-22
Community
Discussions for Nocturne Memory
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude