Integration · JetBrains

Persistent memory for JetBrains IDEs

Install the Cachly Brain plugin from the JetBrains Marketplace. It sets up Junie, AI Assistant and Claude Code in IntelliJ IDEA, PyCharm, WebStorm, GoLand or Rider with one shared memory.

Set it up

  1. Install Cachly Brain from the JetBrains Marketplace (Settings → Plugins). Restart the IDE if it asks. Node.js 20 or newer is required.

  2. Click Use the Brain, then Save my choice, then Set up AI files (also under Tools → Set Up AI Files).

  3. Using AI Assistant? Also click Connect AI Assistant, then enable cachly under Settings → Tools → AI Assistant → Model Context Protocol (MCP).

What happens automatically

Opening a file
The plugin shows known failure patterns for that file when the risk is medium or high.
In the chat
Junie, AI Assistant and Claude Code use the cachly tools to recall and store lessons.

On top of that, JetBrains IDEs can call the cachly tools itself, for example smart_recall before a task and learn_from_attempts after a fix.

Files cachly writes

.junie/mcp/mcp.json, .junie/guidelines.md
Connect Junie and tell it when to use its memory.
.aiassistant/rules/cachly.md
A rule for AI Assistant (only in projects with an .idea folder).
.mcp.json
Connects Claude Code inside the IDE.

Limits

  • AI Assistant reads MCP servers only from its own settings. Its first start with cachly takes about 40 seconds.
  • The MCP settings page may be missing in IDE versions before 2025.3.

Frequently asked questions

Which JetBrains IDEs work?

IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider and the other IDEs on the IntelliJ platform, with Junie, AI Assistant or Claude Code.

Does the plugin change my code?

No. It writes configuration files for the AI tools (for example .junie/mcp/mcp.json) after you click Set up AI files. Your source files stay untouched.

Where is my memory stored?

On cachly servers in Nuremberg, Germany. Your project files hold no key; the key comes from your environment or from ~/.cachly/credentials.json on your machine.

Can my other coding tools use the same memory?

Yes. A lesson stored from one tool is available in every other tool connected to the same Brain, and to teammates who share it. Claude Code, Cursor, GitHub Copilot, JetBrains, Codex CLI and Gemini CLI all read from one Brain.

More about cachly and JetBrains IDEs