Lararium: a clone-and-run template for a personal agentic system. A file-based brain, an assistant soul you talk to, a searchable index, an agent roster you can re-theme, session hooks and skills. The shrine; you bring your own gods.
- capability exposure inferred + 35
- 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.
graded 1m ago · see ecosystem CVEs →
- B · 19 → B · 32
- A · 7 → B · 19
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit d89342c · analyzer v28 · 12h ago
skills & prompt files 11
- agent-rules kylnor-lararium-d89342c/AGENTS.md
- agent-rules kylnor-lararium-d89342c/brain/CLAUDE.md
- skill kylnor-lararium-d89342c/skills/defs/end/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/evolve/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/feature-list/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/handoff/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/in-the-lab/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/model-fusion/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/muninn/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/sessions/SKILL.md
- skill kylnor-lararium-d89342c/skills/defs/upgrade/SKILL.md
[](https://mcpobservatory.com/servers/github:kylnor/lararium/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 kylnor.