plur-memory · plur-ai — Claude Code skill: what it does, how to install
Local-first memory skill that keeps corrections and preferences on your disk. It feeds relevant context into new sessions without cloud servers or API keys.
npx skills add plur-ai/plur --skill clawhub -a claude-codeWhat plur-memory does
plur-memory stores agent preferences and corrections directly on your local disk as plain text files. Your data never touches a remote server. You do not need any API key or subscription. Next time you start a conversation, the skill inserts relevant project habits before you write your first prompt.
The memory engine mimics human retention. Frequently used rules become stronger engrams, while inactive notes fade over time. Because it connects through MCP, lessons learned in Claude Code transfer to Cursor without extra configuration. Running it requires Node.js version 18 or higher alongside OpenClaw 2026.3.7 or newer.
What it helps with
- keep project preferences and corrections on local disk
- inject relevant context at session start without manual notes
- share agent memory between Claude Code and Cursor over MCP
- boost benchmark retrieval rates on LongMemEval without cloud vector stores
Example prompts for the agent
- Remember that we enforce strict types and pnpm across this repository
- Check what local habits and rules are stored from past sessions
- Do not add comments to self-explanatory functions and save this rule
How to install plur-memory
1Skills CLI (Vercel)
npx skills add plur-ai/plur --skill clawhub -a claude-code2Manually: put the files in place
~/.claude/skills/clawhub/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/clawhub/
1Skills CLI (Vercel)
npx skills add plur-ai/plur --skill clawhub -a codex2Manually: put the files in place
.agents/skills/clawhub/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add plur-ai/plur --skill clawhub -a cursor2Manually: put the files in place
.cursor/skills/clawhub/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install plur-ai/plur clawhub2Manually: put the files in place
.github/skills/clawhub/SKILL.md1Skills CLI (Vercel)
npx skills add plur-ai/plur --skill clawhub -a gemini-cli2Platform CLI
gemini skills install https://github.com/plur-ai/plur --path packages/claw/clawhubManually: put the files in place
.devin/skills/clawhub/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add plur-ai/plur --skill clawhub -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about plur-memory
How to install plur-memory in Claude Code?
Run npx skills add plur-ai/plur --skill clawhub -a claude-code in your terminal. The file is added at ~/.claude/skills/clawhub/SKILL.md.
What does plur-memory do?
It records your corrections and workflow preferences into plain local files. When you start a fresh session, it pulls relevant facts into the prompt context automatically.
What are the system requirements for plur-memory?
It requires Node.js 18 or newer and OpenClaw 2026.3.7 or higher. The skill is licensed under Apache-2.0 and integrates with Claude Code, Cursor, and other MCP-compatible tools.
Source text
SKILL.md · Apache-2.0
--- name: plur-memory description: "Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use." version: 0.15.0 --- # PLUR Memory Most memory plugins send your context to a cloud server. PLUR doesn't. Your memory lives on your disk — plain files you can read, edit, move, and back up. Zero cloud routing. Zero API keys. Zero cost. **Install in one command:** ``` openclaw plugins install @plur-ai/claw ``` Or tell your OpenClaw: `go to plur.ai and install memory` ## What happens next Every correction you make becomes a permanent engram. Every preference gets remembered. The next time you open a session, PLUR injects what's relevant — automatically, before you type a word. ## One memory, every tool Correct something in OpenClaw — your Claude Code picks it up. Teach a pattern in Cursor — OpenClaw already knows. Memory moves with you across every MCP-compatible tool you use. ## Features - Learns from corrections and preferences as you work — no manual notes - Injects relevant context at session start — no re-explaining from scratch - Memory strengthens with use, fades when stale — modeled on human memory - Works across Claude Code, Cursor (beta), and any MCP-compatible tool - No cloud, no API key, no cost — by default ## Benchmarks - **Retrieval** (LongMemEval R@5): **76.7%** out-of-the-box · **97.0%** with openai-3-large embeddings — [full methodology](https://plur.ai/benchmark.html) - **Agent tasks**: 89% win rate — Haiku + PLUR outperforms Opus *without* memory - **House rules**: 12–0 across Haiku, Sonnet, Opus ## Open source. Local-first. Private. Free. Apache-2.0. Your data never leaves your machine. ## Requirements - OpenClaw >= 2026.3.7 - Node.js >= 18 ## Links - Website: https://plur.ai - GitHub: https://github.com/plur-ai/plur - npm: https://npmjs.com/package/@plur-ai/claw - Benchmarks: https://plur.ai/benchmark.html **Author:** PLUR ([email protected])
© plur-ai · Apache-2.0 · plur-ai/plur
Similar skills
All skills for Agent setup: memory, context, orchestration →plur-memory by other authors comes first.
