> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kodus.io/llms.txt
> Use this file to discover all available pages before exploring further.

# What is the difference between Review Rules and Memories

> Understand when to use Review Rules vs Memories in Kody for the best code review results.

In the Kody Rules UI, you configure two different things, and knowing when to use each one makes your code reviews more effective.

A useful rule of thumb:

* **Memories** teach Kody how your codebase works so future reviews and suggestions are more relevant.
* **Review Rules** tell Kody what to flag when a PR does not match your standards.

## Review Rules

Review Rules are **traditional code review checks** that run during the dedicated code review stage. They analyze file diffs or the entire PR against your defined criteria.

**Best for:**

* Architecture boundaries ("domain layer must not import infrastructure")
* Code patterns ("avoid `==` in loop conditions")
* PR requirements ("every service file must have a test")
* Structural validation using variables like `fileDiff`, `pr_files_diff`

**How they work:**

* Applied at file-level or PR-level scope
* Run only during code review
* Support file references (`@file`, `@repo`) and MCP functions
* Produce suggestions with severity levels

## Memories

Memories are **persistent contextual instructions** injected across all interactions — code reviews, conversations, and AI suggestions. They represent the background knowledge Kody should carry about your codebase, conventions, and preferences.

**Best for:**

* Codebase context ("this repo mirrors a third-party API, so some external payload fields intentionally stay snake\_case")
* Suggestion preferences ("when suggesting JS utilities here, prefer native methods over Lodash")
* Migration context ("the billing module is mid-migration, so prefer incremental fixes over broad refactors")
* Architectural context ("this service follows hexagonal architecture and keeps adapters at the edge")

**How they work:**

* Injected as high-priority context in all prompts
* Improve future suggestions by grounding Kody in repo-specific context
* Created via conversation (`@kody remember: ...`) or manually in the UI
* Scoped to directory, repository, or organization level
* Kody auto-deduplicates and resolves conflicts between memories

## When to use which

| Scenario                                                                                        | Use         |
| ----------------------------------------------------------------------------------------------- | ----------- |
| Check if a test file exists for every service                                                   | Review Rule |
| "This repo mirrors an external API, so some response fields intentionally stay snake\_case"     | Memory      |
| PR description must follow a template                                                           | Review Rule |
| "Tests in this service usually live next to implementation files, not in a central test folder" | Memory      |
| Flag imports that violate architecture layers                                                   | Review Rule |
| "The auth module is mid-migration, so prefer incremental changes over broad refactors"          | Memory      |

## Can I convert between them?

Yes. In the Pending Memories modal, you can **convert a memory into a Review Rule** if you decide it needs more structured enforcement with file paths and severity levels.

For details, see [Kody Rules](/how_to_use/en/code_review/configs/kody_rules).