Claude Mem

Claude Code is powerful, but it starts every session with a blank slate. You explain your project structure, coding conventions, and past decisions over and over. Claude Mem fixes this by giving Claude Code a persistent memory layer. The plugin works as a lightweight MCP server that Claude Code connects to automatically. When you tell Claude something important — a naming convention, an architectural decision, a bug fix rationale — you can save it to memory with a simple command. On the next session, Claude Code loads those memories as context before it starts working. Memories are stored as structured files in your project directory. Each memory has a category (architecture, convention, decision, bugfix, todo) and a relevance scope (project-wide or directory-specific). This structure means Claude Code loads only relevant memories, keeping the context window clean. The plugin ships with automatic memory extraction too. When Claude Code finishes a task, Claude Mem can prompt it to save key learnings. This creates a growing knowledge base that gets smarter over time. After a week of use, Claude Code knows your project's patterns, your team's style, and your past debugging sessions. Installation takes about two minutes. Clone the repo, add it to your Claude Code MCP settings, and restart. No database to set up, no API keys to configure. Everything lives in your project's .claude-mem directory, which you can commit to git for team sharing. Claude Mem is free and open source. It works with any Claude Code setup — free tier, Pro, or Max. The memory format is plain Markdown, so you can read and edit memories directly if you want more control.