Frequently Asked Questions

Cortex is a memory layer for Claude. It runs quietly on your Mac, captures the corrections and preferences you teach Claude during work, and hands the right context back to Claude at the start of every session. The goal: Claude stops starting from scratch every time you open a conversation.

Anyone who uses Claude daily — developers, designers, writers, researchers, therapists, lawyers, accountants, teachers, marketers. If you've ever re-explained the same preference to Claude more than twice, Cortex is for you.

Claude's current memory is a 200-line markdown index that points to other markdown files you maintain by hand. Every preference, rule, and correction competes for space in that budget.

Cortex replaces that with a structured, neuroscience-grounded system: six layers of memory (sensory, working, episodic, semantic, procedural, long-term), automatic consolidation, decay, and retrieval based on what's actually relevant to your current task. You don't edit files. Cortex watches, stores, and surfaces.

Today Cortex is built for Claude only — it connects through MCP (Model Context Protocol), which Anthropic supports natively in Claude Desktop and Claude Code. MCP is an open standard, so other assistants could integrate with Cortex in the future. Nothing is planned yet.

Soon. We're finishing the last few pieces and preparing for beta. Join the waitlist and you'll be among the first notified.

macOS 14 (Sonoma) and newer at launch. Windows and Linux are on the roadmap but don't have a committed timeline yet. Cortex connects to Claude Desktop and Claude Code on day one; cross-surface sync (Claude.ai, mobile) ships with the paid tier soon after.

If you joined the waitlist, you'll get one email at launch with a download link and setup guide. No newsletter, no drip campaign, no marketing blast. Just the launch note.

Yes. A private beta will come before the public launch. Waitlist subscribers get first access.

Yes. The full Cortex experience — persistent memory, Claude Code and Claude Desktop integration, unlimited rules, unlimited projects, your data on your Mac — is free forever.

The optional Cloud Sync tier at $49/year. It replicates your local memory to Cloudflare so it follows you across Claude surfaces (Claude.ai, mobile, multiple Macs). Everything else is free.

Three reasons: strong privacy defaults (no ad-tech side business), region-specific data residency, and a pricing structure that lets us keep Cloud Sync at $49/year sustainably.

No. The local-only tier is free forever. We make this commitment explicitly because the whole premise of Cortex is that your memory belongs to you — paywalling local functionality would undermine that.

On the free tier: a local SQLite database at ~/.cortex/cortex.db. Nothing is transmitted anywhere. No network calls, no accounts, no server.

On the paid Cloud Sync tier: your memory is replicated to Cloudflare infrastructure (encrypted in transit and at rest), in a region close to you. You can pause or delete it anytime.

Cortex reads the conversation context that Claude shares with it through MCP — specifically, the corrections and rules you ask Cortex to remember. It does not log, transmit, or analyze your broader conversation content. Your chats with Claude stay between you and Claude.

No. Never. Cortex exists to be your memory — not a training set. We do not share, sell, or license your memories to anyone, for any purpose, including AI training.

Yes. One-click export from Settings produces a portable JSON file with every memory, its metadata, and timestamps. Human-readable, re-importable, yours to keep.

Yes. One-click wipe from Settings clears all local memory. Paid-tier users can also wipe their cloud copy from Settings. You can also delete ~/.cortex/cortex.db directly from the Finder.

No. Your waitlist email is used only to notify you at launch. No newsletters, no partners, no third-party sharing. See the privacy policy.

MCP (Model Context Protocol) is an open standard from Anthropic that lets Claude talk to local tools and data sources. Cortex uses MCP to read and write memory during every session. You don't configure anything manually — installing Cortex wires up the MCP connection for both Claude Desktop and Claude Code.

No. When you correct Claude mid-conversation ("don't do X" or "always do Y"), Claude proposes saving the correction as a rule. Accept, and Cortex persists it automatically. You can also open the Cortex app to browse, edit, pin, or delete memories at any time — but day-to-day, it runs in the background.

Cortex organizes memories into six tiers, modeled on how brains actually handle memory:

• Sensory — raw stream of the current session, mostly discarded
• Working — what Claude is actively thinking with right now
• Episodic — specific events, corrections, and decisions
• Semantic — generalized rules and facts that cross every project
• Procedural — skills and workflows (the how)
• Long-term — everything consolidated for the long haul

Memories move between layers over time: specific events get promoted to general rules; rules that aren't reused decay. It's automatic.

When you start a session, Cortex sees the working directory, open files, and conversation context. It ranks memories by relevance to that context — project scope, recency, reuse frequency, and user-pinned importance — and surfaces the top matches to Claude. You can always promote or pin a memory manually if Cortex misses one.

Rob Stout, an independent designer and developer based in the US. Cortex is an indie product — no VC, no quarterly OKRs pushing the roadmap away from the people using it.

Email hello@remembercortex.com. Every message is read by a human. When the product is live, in-app feedback will be available from the menu bar.

Likely, but not yet. When we have enough active users for a community to be useful instead of empty, we'll open one up.