CLAUDE.md is only the short-term layer

Static instructions are great for what every session needs. Architecture decisions, conventions, and the gotchas you learn the hard way need somewhere durable to live.

  • You re-explain your project architecture at the start of every session, or paste it into CLAUDE.md and watch the file balloon.
  • Decisions you made last week are lost. Claude asks the same questions again.
  • CLAUDE.md loads in full every turn. It is not the place for accumulated knowledge.
  • Hours of productive momentum gone, just getting Claude back up to speed.

Basic Memory changes that

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

Retrieved on demand, not loaded every turn

Claude Code searches Basic Memory for the few notes relevant to the current task instead of loading one giant file. CLAUDE.md stays small; Basic Memory holds the rest.

Reads and writes the same graph

Architecture decisions, coding patterns, and project context accumulate as plain Markdown notes. Searchable by full-text, semantic, and graph navigation. Claude 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. No cloud dependency, no vendor lock-in. Open the same vault in Obsidian alongside Claude Code if you want.

Native MCP integration

Basic Memory uses the Model Context Protocol — the same standard Claude Code is built on. The same knowledge graph is also available in Claude Desktop, claude.ai, Cursor, ChatGPT, and any MCP client.

One command to get started

Quick Setup
claude mcp add -s user -t http basic-memory-cloud https://cloud.basicmemory.com/mcp

One command. The `-s user` flag installs the MCP server at the user scope so every Claude Code session picks it up. Use the cloud URL above (free 7-day trial) or run Basic Memory locally for free (`pip install basic-memory && bm mcp` then point Claude Code at the local server). Verify with `claude mcp list`. 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
Basic memory is the missing 'wow' factor in AI chatbots—now I can't imagine Claude or Claude Code without it.
Caleb
Caleb Picker Consulting

Start building with Claude Code

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 Claude Code persistent memory?
Add Basic Memory as an MCP server with one command: claude mcp add -s user -t http basic-memory-cloud https://cloud.basicmemory.com/mcp (or run it locally, free and open source). Claude Code can then search, read, and write notes in your knowledge base in every session.
How is Basic Memory different from CLAUDE.md?
CLAUDE.md is a static instruction file you maintain by hand and that loads in full every session. Basic Memory is a searchable knowledge graph: Claude Code retrieves only the context relevant to the task at hand, and writes new knowledge back as you work. Most teams use both. CLAUDE.md for standing instructions, Basic Memory for accumulated project knowledge.
Does Basic Memory work across multiple repositories?
Yes. Projects in Basic Memory are independent knowledge bases, so you can keep one per codebase or share one across related repos. The same knowledge is also available in Claude Desktop, claude.ai, and any other MCP client.
Does Basic Memory cost anything with Claude Code?
The local version is free and open source (AGPL-3.0) and adds no API costs. It runs on your machine. Basic Memory Cloud, which syncs your knowledge across devices and tools, starts at $15/seat/month with a 7-day trial.