mnemosyne
Provides a secure, auditable mechanism for maintaining agentic context without leaking sensitive data to third-party cloud providers.
Auditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai
- Store and retrieve technical context for AI agents in a local file
- Maintain an auditable history of agent decisions and memory for compliance
- Provide long-term project knowledge to Claude Code and Cursor via MCP
Provides a secure, auditable mechanism for maintaining agentic context without leaking sensitive data to third-party cloud providers. The local-first SQLite architecture mitigates data privacy risks during complex engineering workflows.
Security-conscious engineering teams requiring persistent, auditable memory for AI agents within local development environments.
https://github.com/28naem-del/mnemosyne
By 28naem-del
How to Get It
claude plugins install 28naem-del/mnemosyne
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me store and retrieve technical context for AI agents in a local file
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- The Mnemosyne Project: An Anki Alternative — Hacker News · 25 pts
- Show HN: Mnemosyne Local hierarchical memory engine for AI agents (MCP Native) — Hacker News · 10 pts
- The Mnemosyne Atlas of Aby Warburg, 1924-29 (2013) — Hacker News · 6 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 153 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 153 GitHub stars; contributors unknown; last commit 0d ago; license MIT.