Your AI coding assistants forget everything between sessions. Recallium gives them persistent memory.
Every time you start a new session with Cursor, Claude, Copilot, or any AI coding assistant, you face the same frustrating problem: they've forgotten everything.
"We use TypeScript with strict mode..." "Our API follows REST conventions..." "We prefer functional components..." You say these things every single session.
Yesterday's debugging session, last week's architecture decision, the authentication pattern you established—all gone when you start a new conversation.
Without memory of past solutions, AI assistants suggest approaches you've already tried and rejected. They don't learn from your project's history.
Recallium is a memory layer for coding agents that captures and organizes your development context. Your AI assistants remember decisions, patterns, and solutions across every session, project, and tool.
As you work, Recallium automatically captures important context: code decisions, bug fixes, architectural choices, and implementation details.
Ask your AI "Why did we use PostgreSQL?" or "How did we implement auth?" and get instant answers from your project's memory.
Memory syncs across Cursor, Claude, VS Code, Windsurf, and JetBrains. Context captured in one tool is available everywhere.
Recallium integrates via the Model Context Protocol (MCP), the emerging standard for AI tool integration. Your coding agents automatically store and retrieve context without any extra commands.
Quick setup with npx. Works with Claude Desktop, Cursor, VS Code, and more.
Code with your AI assistant as usual. No special commands needed.
Important decisions and patterns are automatically captured and remembered.
Your AI finds relevant context from any project, any session, instantly.
Recallium provides memory for all major AI coding assistants:
Recallium is free, open-source, and self-hosted. Your data stays on your machine.