plur-memory

A local memory skill for AI agents that keeps remembered corrections and preferences in readable files on your machine. It can share that memory across compatible tools such as OpenClaw, Claude Code, and Cursor.

In plain words
What is it for?
Use it to keep local, transferable agent memory, automatically recall relevant context, and learn from corrections and preferences while you work.
Why use it?
It avoids sending the memory to a cloud service and removes the need to explain the same preferences again in each session. The memory is available across supported tools.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/plur-ai/plur/clawhub
Any agent
npx skills add plur-ai/plur --skill clawhub
Clone the repo
git clone --depth 1 https://github.com/plur-ai/plur

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00531
Opus 5 $0.00020 $0.00266
Sonnet 5 $0.00008 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured yesterday against content hash e68ae13c2cda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plur-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/claw/clawhub/SKILL.md · 60 lines

What it actually says

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
  • 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

Author: PLUR ([email protected])

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 60 lines · 41 tokens per session scan A e68ae13c2cda

Subscribe to this mod's changes

plur-memory is a skill published in the GitHub repository plur-ai/plur (243 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 531 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

membrain

Shared long-term memory over MCP. Call memorycontext once at the start of any session/task to load what is already known; use searchmemory before answering questions about the user or their projects; save durable facts, preferences, and decisions with savememory / savememories. All agents and the user share the same…

SIDDHU123M/membrain-mcp · 67 tokens

recall

Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.

grpcer/ownmem · 66 tokens

mnemo-cortex

Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.

GuyMannDude/mnemo-cortex · 44 tokens

init

Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.

grpcer/ownmem · 43 tokens

ogham-research

Structured memory capture for Ogham shared memory. Use when the user wants to store findings, remember something, save what was learned, or capture a decision. Triggers on "remember this", "store this", "save this finding", "save what we learned", "capture this decision", "log this", or any request to persist…

ogham-mcp/ogham-mcp · 113 tokens

add-memory-system

Research and integrate a new agent-memory repository into Agent Memory Atlas. Use when asked to add, analyze, catalog, or compare a memory system in this repository, including its commit-pinned system report, comparative overview coverage, homepage card, generated site, and validation.

neoneye/agent-memory-atlas · 57 tokens