The recall logic in Second Brain is fully open. Here is why that matters.

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.

Why this matters in practice:

You can audit exactly how your memories are ranked. If a recall result surprises you, you can trace it back to the code that produced it. No guessing about weights or hidden signals.

You can fork it. If the default behavior does not match how you think, you can change it. A few community members have already forked the scoring to weight recency more heavily than we do by default.

You can trust the roadmap less. We might build something you do not want, or stop building entirely. The code existing independently of us means your investment in the system is not tied to our decisions.

The repo is at github.com/rahilp/second-brain-cloudflare. The recall logic specifically lives in the scoring module if you want to start there.

What part of the system would you most want to inspect or change?