Second Brain for Mac and Windows - Your AI memory, everywhere you work

by
The Second Brain desktop app gets you running in five minutes. No terminal. No git. Just download, set a password, and sign into Cloudflare. Then the real magic starts. Persistent memory across every AI tool you use. Recall that just got a lot smarter. Surfaces the right memory, not just the newest one. A knowledge graph that builds itself. Your data in your own Cloudflare account, not ours. Mac and Windows. You asked for the app. You asked for better recall. We shipped both.

Add a comment

Replies

Best

During our v2 launch, you asked for an easier way. Some mentioned being uncomfortable with git. Others flagged the terminal as a barrier. We listened.

This is the Second Brain desktop app and it exists because of your feedback.

Unlike other memory tools, nothing lives on our servers. Your memories are in your Cloudflare account from day one. We literally can't access them.

Here's what we built: Download. Choose a password. Sign in to Cloudflare (or create a free account if you don't have one, we walk you through it). Five minutes later, your Second Brain is provisioned and running on your machine. No terminal. No git. No technical knowledge required.

You get the full v2 experience, recall-by-meaning, the knowledge graph, all of it, running in a native app on Mac or Windows, pre-authenticated and ready to connect to Claude, Cursor, ChatGPT, and your other tools via MCP.

This is what community-driven product development looks like. Thank you for helping us build this. Now come try it, share your thoughts, and let us know what you think.

 Huge congrats on shipping Mac and Windows simultaneously.. Congrats👏 are there any plans down the road for a lightweight mobile app (iOS/Android) or browser extension to capture quick thoughts on the go?

 The extension already ships for Chrome and Firefox, one hotkey to grab a page or your highlighted text. Mobile is still the real gap, and on-the-go capture is why it keeps coming up.

 Genuinely useful problem to solve. One thing I'm curious about: if Claude, Cursor, and ChatGPT are all pulling from the same Second Brain via MCP, is memory scoped per-tool or per-project, or does everything share one pool? I've had moments running multiple agents in parallel this week where I'd actually want strict separation — a debugging session in one tool shouldn't bleed into an unrelated project in another.

💎 Pixel perfection
The your data lives in your own Cloudflare account framing is the part I'd push on, since that's a meaningfully different trust model than most memory tools, but it also means Second Brain's actual behavior depends on a Cloudflare Worker you don't directly control or audit line by line. If the knowledge graph builds itself automatically from what gets stored, is there any way to see or edit what it's inferred about you, or is the graph itself a black box that just quietly shapes what recall surfaces even though the raw memories are yours to inspect. Also, recall surfacing the right memory instead of just the newest one is a meaningful claim, since relevance ranking is exactly where memory tools tend to either feel magical or frustratingly wrong depending on the query. What happens when two memories genuinely conflict, say you noted a preference one way months ago and then said the opposite more recently, does recall favor recency, relevance to the current prompt, or does it surface both and let the connected AI tool sort it out.

 Not a black box. The dashboard has a graph view where every edge carries a weight and its provenance, and if a link is wrong you can unlink it there, from any MCP client, or via the API. Weak inferred edges also get pruned nightly, so bad guesses fade instead of hardening into your model of you. On conflicts, it surfaces both. Promote a memory to canonical and it is protected, and a contradicting newcomer lands as a draft for reconciliation instead of overwriting it. Recall favors what survived the challenge rather than what arrived last. Recency alone was how we got confidently wrong answers.

The no-terminal, pre-authenticated setup is a smart move for adoption. One question does the desktop app sync memories in real-time across multiple devices, or is it single-machine only for now?

 Nothing to sync. The app is a client, the brain is one Worker in your Cloudflare account, so every machine reads and writes the same memory.

   I was wondering the same thing. Thanks for asking

The problem you are solving is so real, I keep re-explaining my whole project to every new chat like it is our first date. One click deploy to Cloudflare sounds lovely. If I use it with both Claude and Cursor, do they share the exact same memory pool or can I split things per tool?

 Same pool by default, and that is the point. Cursor picks up what Claude learned without you retyping it. Tags are how you split things today, scope a recall to one tag and the rest stays out. Per-tool partitioning is on the roadmap.

Congrats, one thing I'm wondering about though, once it's provisioned on your own cloudflare account, how does syncing work across multiple machines, is it pulling from the same cloudflare instance or does each install create its own graph that needs merging. asking because that's usually where "your data, your account" setups get messy.

 One brain, not one per install. The second machine signs into the same Cloudflare account and points at the same Worker, so there is nothing to merge. The app is only a client on top of it.

that's really clever. how does it handle when two memories contradict each other?

 Both surface. Canonical stays protected, the newcomer lands as a draft.

The trajectory of the usefulness of this tool will only continue to rise as time passes and we have too many tools to count— nice work on this— are you planning on going a similar direction as obsidian or a different one?

 Different one. Obsidian is a vault you write in and file by hand. Second Brain is memory your AI tools write and resolve on their own, so it gets more useful with every tool you add, not with every note you take.

Congrats on shipping this. Self hosted on my own Cloudflare account with MCP support is exactly the setup I want for memory, no third party holding my context. How does the duplicate detection work when two memories say roughly the same thing in different words, does it merge them or keep both?

 Similarity decides. Above 0.95 the write is blocked. Between 0.85 and 0.95 an LLM judges merge, replace, or keep both, weighted by importance. High value memories resist collapsing, so nuance survives instead of getting flattened into one line.

We’re live! 🎉

I’ve been up since early this morning watching the comments come in and it already means a lot.

This app exists because of this community. You told me the setup was too hard. You asked for a no-code path. I built it.

Download, set a password, sign into Cloudflare. Five minutes. No terminal. No git. Your Second Brain is running natively on Mac or Windows, connected to every AI tool you use via MCP.

Your memories live in your Cloudflare account. Not mine. I literally cannot access them.

If you try it today, tell me where it breaks, where it confuses you, and what you want next. That feedback is what shapes the next version.

Let’s go.

congrats on making this a real desktop app - the git/terminal barrier was a legit dealbreaker for a lot of people on the v2 launch. since it's pre-authenticated to Cloudflare on setup, does the app ever need you to re-auth or re-enter your password day to day, or is it truly a one-time five minute setup and then it just runs in the background like any other memory tool from then on?

 One time. Your password is the auth token and it lands in your OS keychain at setup, so you only retype it when connecting a second machine. The brain itself is a Worker in your own Cloudflare account, so it keeps answering Claude and Cursor whether or not the app is open. The app is the installer and control panel, not the thing that has to stay running.

123
Next