A persistent memory rule that stores and recalls workspace context across sessions. It uses tags to filter memories and requires the agent to discover the available memory tools before using them.

Use it to recall project preferences, past fixes, and other stable workspace information, and to save selected context for later sessions.

It reduces the need to repeat useful project context in every session. Tag filtering can prevent unrelated memories from being returned, but missing or incorrect tags can exclude relevant information.

automem — Cursor rule for Cursor by verygoodplugins/mcp-automem

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/verygoodplugins/mcp-automem

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/verygoodplugins/mcp-automem/automem/github.svg)](https://agentmods.dev/rules/verygoodplugins/mcp-automem/automem)

Your own site

<a href="https://agentmods.dev/rules/verygoodplugins/mcp-automem/automem"><img src="https://agentmods.dev/badge/rules/verygoodplugins/mcp-automem/automem/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/verygoodplugins/mcp-automem/automem"><img src="https://agentmods.dev/badge/rules/verygoodplugins/mcp-automem/automem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,201 This file is loaded in full into every session.

When invoked 2,201 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.

Model	Per session	Once invoked
Fable 5.1	$0.02201	$0.02201
Opus 5.5	$0.00880	$0.00880
Sonnet 5.5	$0.00440	$0.00440
Haiku 4.5	$0.00220	$0.00220

Measured yesterday against content hash 74b39a459905, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

automem 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.

plugins/automem/rules/automem.mdc · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoMem Memory Integration

Use AutoMem proactively to maintain persistent context across sessions for the current workspace. Preserve host/platform instructions; this rule ships with the AutoMem plugin and applies to every workspace. The project slug is the workspace folder name, lowercased with hyphens (written as <workspace-folder-slug> below); the plugin's session-start hook derives it for you.

Cursor MCP server: memory. Discover its tools before the first call and use the live tool inventory. Cursor may expose server-local tool names through its MCP dispatcher or direct callable names. The examples below use the direct spelling mcp_memory_* (e.g. mcp_memory_recall_memory); when a dispatcher is available, target this server and the corresponding unprefixed tool name instead.

Tool's real behavior (validated against production corpus)

Tags are a hard gate - memories without matching tags are excluded before scoring. Use tags for stable categories like preference and bugfix; do not guess topic tags.
One good query beats queries[] + auto_decompose for focused tasks. Use queries[] only for genuinely multi-topic questions.
limit caps at 50. Routine recall should use enough budget to be useful.
Default text format shows content previews with created/updated timestamps and importance. detailed adds type/confidence/metadata summary. Responses are budget-capped; fetch a full record with recall_memory({ memory_id }).
store_memory can silently fail. Verify important stores by recalling a distinctive phrase; retry once if missing.
Bare tag convention - Use bare tags only. No namespace prefixes (project/*, lang/*), no platform tags, and no date-stamped tags. Keep source attribution in metadata and dates in timestamp / t_valid / t_invalid. Use automem, not project/automem. entity:*:* tags are server-injected.

Read the full file on GitHub · 159 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.

yesterday First seen · 159 lines · 2,201 tokens per session scan A 74b39a459905

Subscribe to this mod's changes

automem is a cursor rule published in the GitHub repository verygoodplugins/mcp-automem (66 stars, last pushed today), licensed MIT. It adds 2,201 tokens to every session, about $0.0088 per session on Opus 5.5. 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 2026-11-05.

Memory and context ai falkordb graph-database nodejs qdrant

automem next to 6 cursor rules from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
automemverygoodplugins/mcp-automem	Cursor rule	66	today	MIT	A	2,201	Cursor
mongodb-memory-server-setupprisma/orm	Cursor rule	48k	yesterday	Apache-2.0	A	28	Cursor
cursor-rulesMatthewSherlin/mushroomdb	Cursor rule	5	today	none	A	1,337	Cursor
ponytailDietrichGebert/ponytail	Cursor rule	185k	8d ago	MIT	A	604	Cursor
angular-20angular/angular	Cursor rule	101k	yesterday	MIT	A	0	Cursor
dev-standardapache/superset	Cursor rule	75k	today	Apache-2.0	A	1,147	Cursor
prefer-direct-imports-over-module-mocksprisma/orm	Cursor rule	48k	yesterday	Apache-2.0	A	0	Cursor