udjin-labs/mnemostack
Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.
4 starsPythonApache-2.0agent-memoryai-agentshybrid-retrievalllm-memory
SCANNED61/100
Scanned 2026-06-22 · gemini v1
Dimension breakdown
Security
15/100
5 findings
Quality
92/100
3 findings
License
90/100
No findings
Completeness
55/100
3 findings
Findings (11)
CRITICAL: 3HIGH: 1MEDIUM: 4LOW: 1INFO: 2
- CRITICALsecurityArbitrary Code Execution via Dynamic Module Loading (--enrich)
- CRITICALsecurityUnauthenticated API Exposure (HTTP Server)
- CRITICALcompletenessMissing README.md with client installation instructions
- HIGHsecurityPath Traversal / Arbitrary File Read in `cmd_index`
- MEDIUMsecurityPotential NoSQL/Graph Injection via `--filters`
Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.
Maintainer of this repo?
Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.
Claim listingEmbed the badge.
Drop it into your README. Every view backlinks to this verification page.
Markdown
[](https://archimedes.market/r/udjin-labs/mnemostack)HTML
<a href="https://archimedes.market/r/udjin-labs/mnemostack"><img src="https://archimedes.market/api/badge/udjin-labs/mnemostack.svg" alt="Archimedes Trust Verified"/></a>