v2 is almost here. Try the release candidate before July 12.

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.

There's also an explicit trust model now. Canonical memories are protected. When something new contradicts them it gets flagged as a draft rather than silently overwriting what you've confirmed. The memories that have held up over time carry more weight in recall.

V2.0.0-rc.3 is live on GitHub right now. Stable drops July 12.
https://github.com/rahilp/second-brain-cloudflare/releases/tag/v2.0.0-rc.3

If you've been using v1, this is worth a look before launch. What breaks? What doesn't make sense? Feedback between now and the 12th shapes what ships as stable.