Guide · Claude memory

Claude Memory: what it remembers, what it forgets, and how to fix it

Claude does have a memory now — several, actually. They're useful, and they're smaller than the name suggests. This page explains what Claude's built-in memory actually holds, the three places where it stops, what the popular do-it-yourself answer looks like, and where that one breaks too.

What Claude's built-in memory actually does

On claude.ai, Claude maintains a memory summary drawn from your conversations — you can read, edit, and delete it in your Claude settings, and memory is scoped so that separate projects keep separate context. Files you add to a Project are available in every chat inside that Project. Claude Code, the terminal agent, reads Markdown memory files (CLAUDE.md and auto-memory notes) at the start of each session. All of this is real, documented behavior — Anthropic's own docs describe each layer, and within its scope each one works.

Where it stops: three limits

The DIY route: CLAUDE.md, Markdown files, Git

The most popular answer to these limits is to build your own: keep your knowledge in Markdown files, point Claude Code at the folder, version it with Git. It's a good answer — free, local, transparent, and for plain text it genuinely works. Half the Claude Code community runs on some variant of it, from a single CLAUDE.md to elaborate memory directories. If your knowledge is text you wrote yourself, you can stop reading here.

Where the DIY route breaks: scanned documents

Real knowledge doesn't arrive as tidy Markdown. It arrives as PDFs, receipts, contracts, scans, mail attachments. Markdown folders have no answer for those — a scan in a folder is a file name, not knowledge. Users of these systems say it themselves; in a Mac Power Users thread, an Evernote emigrant described Obsidian as "good at text only/minimal images", with getting receipts and scans in being "clunky". That's the honest boundary of the DIY route: it holds what you typed, not what you received.

What a document memory looks like

A memory that includes documents has to read them. Memexa runs every upload through OCR, splits it, embeds it, and distills it into linked notes in a knowledge graph — so a search hit can say "contract, page 4" instead of "somewhere in your files". Claude reads and writes this memory over MCP, and so does every other MCP client. Connecting takes one URL:

claude mcp add --transport http --scope user memexa https://brain.memexa.ai/mcp

Settings → Connectors → Add custom connector → https://brain.memexa.ai/mcp

Sign in once in the browser (OAuth 2.1), no tokens to copy. Full setup for every client is on the how-it-works page. Keep the built-in memory and the Markdown folder — they don't conflict. The document layer is what they're missing.

Where your data lives

A memory is a strange thing to rent, so the exit has to be real: Memexa hosts in the EU under the GDPR, your content is never used for training, and everything exports as Markdown with one click — the graph is an index, not a lock-in. Details in the privacy policy.