Vaultr Memory

Extracts identity/preferences/goals/beliefs/people/state from Vaultr notes with decay-based memory files.

Works with setup

Test report

Verdict
Works with setup
Score
8.8/10
Tested
Jul 15, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 6a49486

The classification rules are the real value: it correctly tells the agent to pull only a dated personal stance (the '立场' section) from a podcast summary and explicitly NOT extract the podcast's guests as 'people' - a distinction a naive prompt would miss - but none of this runs without the proprietary Vaultr desktop app, its `vaultr` CLI, and a pre-existing vault.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 4/5

What Vaultr Memory does

Scans a Vaultr vault's short notes and knowledge base and writes six structured memory files (identity, preferences, goals, beliefs, people, state) with seen/last/decay-window tracking, so facts that stop being reinforced fade and are eventually deleted. Triggers on 'update my memory', 'extract memories from notes', or 'refresh personal memory base' - but it only functions inside the Vaultr app, via its `vaultr` CLI, against an existing populated note vault.

How to install Vaultr Memory

git clone https://github.com/skoowoo/vaultr-notes.git
cd vaultr-notes
mkdir -p ~/.claude/skills
cp -r skills/vaultr-memory ~/.claude/skills/vaultr-memory

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Vaultr Memory

  • /vaultr-memory Extracts identity/preferences/goals/beliefs/people/state from Vaultr notes with decay-based memory files.

It also activates on plain-language prompts like these:

  • refresh my personal memory base from my latest Vaultr notes
  • extract my identity and goals from my vault notes into memory files
  • update my beliefs and preferences memory from recent vault entries

Frequently asked questions

Is the Vaultr Memory skill free?
Yes. The skill itself is free from skoowoo/vaultr-notes. SkillProof publishes the install command and an independent test verdict at no cost.
Does Vaultr Memory work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. The classification rules are the real value: it correctly tells the agent to pull only a dated personal stance (the '立场' section) from a podcast summary and explicitly NOT extract the podcast's guests as 'people' - a distinction a naive prompt would miss - but none of this runs without the proprietary Vaultr desktop app, its `vaultr` CLI, and a pre-existing vault.
What is the Vaultr Memory SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Vaultr Memory?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Vaultr Memory with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.