How AI Works at KindMind

This page explains how AI features at KindMind actually work. That includes the Guide chat (an AI-guided self-reflection conversation), the memory it builds from your conversations over time, and the Journal memory setting that decides whether your journal entries feed that memory too.

The short version: your writing stays encrypted on our servers. When you talk to your guide, your messages travel through a small piece of infrastructure we run, then to Anthropic’s Claude API, then back to you. Nothing you write is stored along the way, though an automated safety check now runs on that trip too (more on that below). Your guide always remembers your conversations with it. Whether it also learns from your journal entries is up to you, and everything remembered is summarized and re-encrypted before being saved back.

Does This Apply to You?

It depends on your plan. On the Journal plan, your journal entries are never sent to AI. There’s no Guide chat, no memory, none of the infrastructure described below touches your writing at all. That’s the whole point of it.

On the Guide and Completeplans, AI features are available: the Guide chat, and (on Complete) Paths. Everything below, the data flow, the safety check, memory summarization, describes how those features work. Journal memory, specifically whether your journal entries feed the AI’s memory, stays off until you turn it on. Your guide always remembers your conversations with it either way.

The Data Flow

When you send a message in the Guide chat, it takes this path:

• Your browser decrypts the conversation locally using your master key, then sends the message over HTTPS.
• It travels to a small KindMind worker (a Cloudflare edge proxy at ai-proxy.kindmind.com) that verifies a short-lived token bound to your session.
• Before forwarding your message, the worker runs a quick automated safety check: a second, separate call to the same Anthropic API, under the same no-training, no-retention configuration, that looks for signs of crisis or risk.
• The worker forwards the request to Anthropic’s Claude API.
• Claude’s reply streams back through the worker to your browser, which decrypts and renders it. If the safety check flags a serious concern, the worker skips the AI reply and sends a fixed supportive message with crisis resources instead.

Plaintext exists only briefly, in transit through the worker, including during the safety check above. The worker doesn’t log message bodies, doesn’t store them, and has no database. The worker keeps no memory of past requests. If the safety check flags a concern, KindMind keeps a category-level record of that (never the words themselves) so we can point you toward support, described more below.

What “Summarization” Means

Once a day, KindMind takes your recent records (your conversations with the guide, and your journal entries if Journal memory is on; the first pass covers your 25 most recent records per feature), decrypts them in your browser, and sends them through the worker once. Claude returns a short summary. That summary is then re-encrypted with your master key and saved to your Memories.

From that point on, your guide sees the summary, not the original entries. As you keep writing, new records are folded into your memory periodically, the same way. The original 5,000-word journal entry never sits in an AI’s context window. Just the gist of it.

What Gets Stored, and Where

Memories live in a table called user_memories, encrypted with your master key. Your master key never leaves your device. To us, a memory looks like a random string of bytes.

Your original records (journal entries, path responses, guide chat messages) stay encrypted in their own tables. Memory building doesn’t copy them anywhere new. It distills them into a separate memory blob that lives alongside.

You can read more about how master keys, password-derived keys, and the underlying encryption work on the encryption page.

Anthropic’s Posture

Claude is built by Anthropic. We use the claude-sonnet-4-5 model via their commercial API.

Anthropic’s commercial API does not train on the messages that flow through it. Their published policy is zero data retention for API traffic when configured that way, and our worker requests are configured for it. They also publish their data privacy practices at anthropic.com/legal/privacy if you want to read it directly.

In practice: your message is processed long enough to generate a reply, then dropped. It isn’t retained, reviewed, or used to make future models smarter, whether it’s the main conversation or the automated safety check that runs alongside it.

What KindMind Never Sees

KindMind’s servers only ever see encrypted blobs and IVs(the random bits that make each encryption unique), non-sensitive metadata like timestamps and record counts, and, when the safety check above flags a concern, a category-level safety record (for example, “crisis resources shown”). If the check itself fails to run, we also store a content-free error record so we can keep an eye on it. We also keep anonymous records of each time the safety check runs, noting the category it saw and how long it took. Those records are never tied to you and never include your words. We never see:

• The plaintext of your journal entries, path responses, or guide chat messages
• The plaintext of your memory summaries
• Your master key or your password
• The content of your conversations with Claude

The Guide chat and the memory summarization both go through the worker, which is a separate piece of infrastructure from the main KindMind app. The main app never receives that traffic, with one narrow exception: chat messages (not memory summarization) get an automated safety check, and when that check flags a concern (or fails to run), the worker sends KindMind a category-level record instead of the conversation itself.

How to Turn It Off

Journal memory is fully optional and reversible. Open Account → AI features → Journal memory. From there you can:

• Turn Journal memory off. From then on, no journal entries are ever sent to AI. Your guide keeps remembering your conversations with it.
• Click Clear all AI memories to wipe the slate. Memory building starts fresh from there.

Turning Journal memory off stops journal entries from contributing new summaries going forward; memories created earlier stay until you clear or edit them. Clearing memories deletes what’s already there. Both are immediate.