When your AI remembers something, it treats every piece of context with the same weight. A decision you made six months ago sits alongside a rough idea you were brainstorming yesterday. There is no way to say "this is settled" versus "this was just thinking out loud."
When an AI system decides what context to surface, you are usually trusting a black box. You do not know exactly why one memory ranked higher than another, or how the system handles edge cases.
Second Brain v2 is fully open source. The recall scoring, the graph traversal, the conflict detection logic, all of it is readable.
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.
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.
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.
