.cursorrules is only the short-term layer

Cursor rules cover style and conventions. The architecture decisions, refactor history, and gotchas need somewhere durable to live.

  • Every Cursor session starts cold. Your AI forgets all prior project context.
  • You re-explain architecture, conventions, and decisions over and over.
  • .cursorrules helps with style, but it can't capture evolving project knowledge.
  • Complex refactors stall because Cursor can't recall what you decided last session.

Basic Memory changes that

Give Cursor a persistent, searchable knowledge base it can read and write to.

Retrieved on demand, not loaded every turn

Cursor's agent searches Basic Memory for the few notes relevant to the current task instead of loading one giant file. .cursorrules stays small; Basic Memory holds the rest.

Reads and writes the same graph

Architecture decisions, patterns, and project context accumulate as plain Markdown notes. Searchable by full-text, semantic, and graph navigation. The agent reads them when relevant and writes new ones as work progresses.

Plain Markdown you own

Every note is a file on your disk. Read, edit, and version with Git. The same vault works in Claude Code, Codex, ChatGPT, and any MCP client.

Native MCP integration

Cursor supports MCP servers natively. Basic Memory plugs right in. No extensions or workarounds.

One command to get started

Quick Setup
{"mcpServers":{"basic-memory-cloud":{"url":"https://cloud.basicmemory.com/mcp"}}}

Paste this in Cursor → Settings → MCP → Add new MCP server, or write it to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` in your project. Restart Cursor and the agent picks up the new tools. For local mode, swap the URL block for `{ command: 'bm', args: ['mcp'] }` after installing Basic Memory (`pip install basic-memory` or `brew install basic-memory`). Full setup guide →

What users are saying

Basic Memory changed my whole relationship with LLMs... I switched from GPT and Gemini to exclusively Claude and Claude Code because of this integration and am completely revamping all our companies processes around a basic memory workflow now.
Alex
TrainerDay
I don't code without Basic Memory anymore. It's such a time saver to be able to refer to projects I don't currently have active and keep a running log of all of my learnings and ProTips. Absolutely love it.
@groksrc
Developer

Start building with Cursor

Try Basic Memory free for 7 days. Your notes stay yours either way.

7-Day Free Trial

$15/seat/month
Graduated team pricing
  • AI collaboration via MCP
  • Shared workspaces for teams and agents
  • Team member management and audit logs
  • Full-text search across notes and projects
  • Desktop, mobile, and web access
  • Private, exportable Markdown files
  • 50,000 notes per seat
  • 1,000 note updates per seat per day
  • Cancel anytime, your data stays yours

Open source available for power users

View on GitHub

Frequently asked questions

How do I give Cursor persistent memory?
Add Basic Memory as an MCP server in Cursor’s settings (Settings → MCP). Cursor’s agent can then search your knowledge base before answering and save decisions and context as you work. Memory that persists across sessions and projects.
How is Basic Memory different from Cursor rules?
Cursor rules are static instructions you write by hand. Basic Memory is retrieved knowledge: searchable notes about your architecture, past decisions, and project history that the agent pulls in only when relevant. And can update itself. They complement each other.
Does Basic Memory work with other editors too?
Yes. The same knowledge base works in VS Code, Claude Code, Codex, ChatGPT, Claude Desktop, and any MCP client. And the underlying files are plain Markdown you can read in any editor, including Obsidian.