Shipped v1.10 yesterday. Redeploy only, no migration.
The thing that was broken: ask your memory store for something specific, like a version string or an error code, and it'd come back with the wrong thing. Confidently. Dense search embeds those identifiers so close together it can't tell them apart. It's not a miss, it's a wrong answer that looks right.
Every AI conversation starts from zero. Your projects, decisions, and preferences disappear as soon as you close the chat. Second Brain fixes that. It is a self-hosted memory layer that works with Claude, ChatGPT, Cursor, and any MCP client. You can store context once and recall it by meaning instead of keywords. It includes duplicate detection, semantic search, and a web UI. Built on Cloudflare, it offers a free tier and your data remains yours. MIT licensed.
V1 shipped persistent memory across Claude, ChatGPT, Cursor, and every other MCP client. V2 takes that further: every memory you save now links itself to related ones automatically. The graph builds itself. Ask a question and recall expands outward, surfacing context you didn't think to ask for.
I've noticed more people using second-brain in ways I didn't expect when I created it, and I want to record that somewhere.
This thread is for sharing how you actually use the REST API or CLI in your daily routines. I m not looking for the obvious tips from the README, but rather the workflows you've created, the scripts you're running, and the things that turned out to be more helpful than you thought.
Until now your MCP endpoint was protected by URL obscurity. The random Worker URL generated at setup made it hard to guess. That worked, but it was not real security. @phillipadsmith pointed this out and shipped a PR to fix it. v1.7 adds proper OAuth so the endpoint is explicitly protected, not just obscure.
Merging also got smarter. When two memories overlap, v1.7 now weighs importance, so high-signal context does not get flattened into a near-duplicate. This one came directly from feedback by @anand_thakkar1 during the launch.
I built Second Brain because I kept hitting the same wall.
I'd have a really productive session with Claude, talk through an architecture decision, get to a clear conclusion, close the tab. Next day I'd open a new chat and have to explain everything from scratch. Same thing with Cursor. Same thing with ChatGPT. Every tool starts fresh, every time.
