Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.
- capability exposure inferred + 22
- tool safety inferred + 12
- supply-chain attested + 6
- trust mitigators mixed − 11
attested 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.
graded 6m ago · see ecosystem CVEs →
- C · 37 → B · 29
- C · 57 → C · 37
- C · 49 → C · 57
- B · 19 → C · 49
- A · 0 → B · 19
No known CVEs for this server.
- high dangerous code
committed secret: GitHub token
analyzed v0.6.82 · analyzer v33 · 2d ago
skills & prompt files 10
- skill majiayu000-remem-80acc68/.agents/skills/remem-first-run-smoke/SKILL.md
- skill majiayu000-remem-80acc68/.agents/skills/remem-plugin-version-sync/SKILL.md
- agent-rules majiayu000-remem-80acc68/AGENTS.md
- agent-rules majiayu000-remem-80acc68/CLAUDE.md
- skill majiayu000-remem-80acc68/plugins/remem/skills/remem/SKILL.md
- prompt-file majiayu000-remem-80acc68/prompts/compress.txt
- prompt-file majiayu000-remem-80acc68/prompts/dream.txt
- prompt-file majiayu000-remem-80acc68/prompts/observation.txt
- prompt-file majiayu000-remem-80acc68/prompts/summary.txt
- prompt-file majiayu000-remem-80acc68/prompts/task_observation.txt
danger signals1
- committed secret GitHub token majiayu000-remem-80acc68/src/memory/retrieval_enrichment/tests.rs :143
ghp_01…(40 chars, redacted)
- supply-chain +6 supply-chain hub →
[](https://mcpobservatory.com/servers/github:majiayu000/remem/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 majiayu000.