What is plur CLAUDE.md?

Project instructions for plur-ai, a system that stores useful facts about past work so AI agents can recall them across sessions, tools, and machines. It describes the project, its packages, dependencies, and versioning.

Use it when developing plur-ai, changing package dependencies, updating versions, or working in its pnpm monorepo, a repository containing multiple related packages.

It gives an agent the project context needed to work consistently with plur-ai and its multiple packages.

plur CLAUDE.md — Instructions file for coding agents by plur-ai: Project instructions for plur-ai, a system that stores useful…

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 instructions/plur-ai/plur/claude-md

Clone the repo

git clone --depth 1 https://github.com/plur-ai/plur

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/plur-ai/plur/claude-md.svg)](https://agentmods.dev/instructions/plur-ai/plur/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/plur-ai/plur/claude-md"><img src="https://agentmods.dev/badge/instructions/plur-ai/plur/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,503 This file is loaded in full into every session.

When invoked 4,503 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.04503	$0.04503
Opus 5	$0.02252	$0.02252
Sonnet 5	$0.00901	$0.00901
Haiku 4.5	$0.00450	$0.00450

Measured today against content hash be3593e4a59a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

plur CLAUDE.md 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 today.

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.

CLAUDE.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

What is PLUR

Persistent memory for AI agents. An agent corrected on Monday remembers on Tuesday — across sessions, tools, and machines.

Knowledge is stored as engrams — small assertions that strengthen with use and decay when irrelevant, modeled on human memory (ACT-R activation). Storage is plain YAML on disk. Search is fully local: BM25 + BGE embeddings + Reciprocal Rank Fusion. Zero API calls, zero cloud.

Seven packages (four npm, three Python/PyPI):

@plur-ai/core        — engram engine (learn, recall, inject, search, decay, sync)
@plur-ai/mcp         — MCP server (Claude Code, Cursor, Windsurf)
@plur-ai/claw        — OpenClaw ContextEngine plugin
@plur-ai/cli         — CLI (plur learn / recall / inject / status)
plur-hermes          — Hermes Agent plugin (Python, via CLI bridge)
plur-ai              — Python SDK (LangChain, llama.cpp, scripts)
plur-langchain       — LangChain BaseMemory + BaseChatMessageHistory adapter

Core is the engine. MCP and Claw are thin wrappers — MCP exposes tools via Model Context Protocol, Claw hooks into OpenClaw's lifecycle (auto-inject on session start, auto-learn on corrections).

Development

pnpm monorepo. From repo root:

pnpm install
pnpm build
pnpm test

~3500 tests across ~200 files (Vitest + Python suites). All must pass before committing.

Package dependency

@plur-ai/core  ←  @plur-ai/mcp
               ←  @plur-ai/claw

MCP and Claw depend on core via workspace:*. Claw imports from core's built dist, not source — after changing core, rebuild before running claw tests:

pnpm --filter @plur-ai/core build

Version bumps

scripts/release.sh is the authoritative source. Two independent version tracks:

Standard release (core / mcp / cli / hermes / python — always bumped together):

packages/core/package.json
packages/mcp/package.json
packages/cli/package.json
packages/migrate/package.json — ships with the release it migrates TO
packages/mcp/src/version.ts — export const VERSION (index.ts and server.ts import it; version-parity.test.ts guards it)
packages/cli/src/version.ts — CLI_VERSION (index.ts and mcp-config.ts import it; pins npx-fallback MCP entries, #1069; version-parity.test.ts guards it)
packages/mcp/test/server.test.ts — version assertions
packages/hermes/pyproject.toml
packages/hermes/plugin.yaml — top-level version: field
packages/hermes/plur_hermes/skills/plur-memory.SKILL.md — frontmatter version:
packages/hermes/plur_hermes/bridge.py — _NPX_CLI_VERSION
packages/python/pyproject.toml
packages/python/plur_ai/bridge.py — _NPX_CLI_VERSION
skills/plur-memory/SKILL.md — frontmatter version: (standalone skills.sh copy)
server.json — both top-level version and packages[0].version (MCP Registry / ClawHub listing)

Read the full file on GitHub · 320 lines

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.

today Changed · -3 lines · -6 tokens per session be3593e4a59a
6d ago First seen · 323 lines · 4,509 tokens per session scan A 400c4ecb0eab

Subscribe to this mod's changes

plur CLAUDE.md is an instructions file published in the GitHub repository plur-ai/plur (245 stars, last pushed today), licensed Apache-2.0. It adds 4,503 tokens to every session, about $0.0225 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.

LLM Memory and context agent-memory ai-agents ai-memory context-engine local-first

plur CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

What is PLUR

Development

Package dependency

Version bumps

What this file has done since we first saw it

Other instructions, from other repositories

remnic AGENTS.md

honcho CLAUDE.md

zer0dex AGENTS.md

memohood AGENTS.md

cli AGENTS.md

wanyimem AGENTS.md