universal-memory

universal-memory is a cursor rule for Cursor from nnaveenraju/sovereign-universal-memory-mcp. It costs 208 tokens per session, scanned A, original, Apache-2.0.

A set of rules for connecting an AI agent to Universal Memory, a system that stores information for use across sessions.

In plain words
What is it for?
Use it to save memories when asked, recall useful context, and record preferences, project knowledge, and error-fix patterns.
Why use it?
It helps retain relevant project details, user preferences, decisions, and lessons from earlier work.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to save memories when asked, recall useful context, and record preferences, project knowledge, and error-fix patterns.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/nnaveenraju/sovereign-universal-memory-mcp/universal-memory
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.

Clone the repo
git clone --depth 1 https://github.com/nnaveenraju/sovereign-universal-memory-mcp

Made for: Cursor.

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.

agentmods badge for universal-memory

README.md
[![agentmods](https://agentmods.dev/badge/rules/nnaveenraju/sovereign-universal-memory-mcp/universal-memory.svg)](https://agentmods.dev/rules/nnaveenraju/sovereign-universal-memory-mcp/universal-memory)
Your own site
<a href="https://agentmods.dev/rules/nnaveenraju/sovereign-universal-memory-mcp/universal-memory"><img src="https://agentmods.dev/badge/rules/nnaveenraju/sovereign-universal-memory-mcp/universal-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 208 This file is loaded in full into every session.
When invoked 208 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00208 $0.00208
Opus 5 $0.00104 $0.00104
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 8d ago against content hash 3f735a902584, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

universal-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 8d ago.

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.

hooks/cursor_hooks/.cursor/rules/universal-memory.mdc · 24 lines

What it actually says

Universal Memory Integration

You have access to a Universal Memory system via MCP that persists knowledge across sessions.

Memory Commands

When the user says "remember that..." or "note that...", store it as a memory using the memory.store tool. When you need context about the project or user preferences, use memory.recall to search for relevant memories.

Auto-Behaviors

  • When you detect user preferences ("I prefer...", "always use..."), store them as identity memories
  • When you fix an error, store the error→fix pattern as a process memory
  • When you discover tech stack details, store them as domain memories

Memory Categories

  • identity: User preferences, style, personal info
  • domain: Project knowledge, tech stack, architecture
  • process: Workflows, debugging strategies, best practices
  • episodic: Session outcomes, decisions, recent activity
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. 8d ago First seen · 24 lines · 208 tokens per session scan A 3f735a902584

Subscribe to this mod's changes

universal-memory is a cursor rule published in the GitHub repository nnaveenraju/sovereign-universal-memory-mcp (0 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 208 tokens to every session, about $0.0010 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 2026-08-31.