Local-first knowledge-graph memory layer for AI agents — what Mem0 charges for: 4-way RRF + L2 maintenance + bilingual classifier, one local SQLite. usearch f16 runs it on $10/year VPS.
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 3d ago · see ecosystem CVEs →
- C · 53 → D · 64
- B · 23 → C · 53
- A · 0 → B · 23
No known CVEs for this server.
- high dangerous code
dynamic exec: __import__ sink, __import__() · credential logged in 1 file(s)
analyzed commit 67e4875 · analyzer v33 · 1w ago
skills & prompt files 1
- agent-rules chinesewebman-mnelo-67e4875/docs/AGENTS.md
danger signals3
- dynamic code execution __import__ sink chinesewebman-mnelo-67e4875/scripts/import_holdings.py :31
STATE_DIR = Path(__import__("os").environ.get("MNELO_STATE_DIR", str(Path.home() / ".hermes" / "state"))) - dynamic code execution __import__() chinesewebman-mnelo-67e4875/tests/test_mcp_sse_cli_round10.py :366
__import__(lib) - credential in logs credential in log chinesewebman-mnelo-67e4875/mcp_transports.py :630
logger.info("streamable_http auth: Bearer token loaded (length=%d chars)", len(auth_token))
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:chinesewebman/mnelo/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of chinesewebman.