We launched here on Monday. The comments were less about the pitch and more about trust: how does this decide what my agent sees, and what happens to that decision when my code moves. So that is where the week went.

You can now mark the files and symbols that always matter, in secondos.yml or from the dashboard if you never open a terminal. The part worth caring about is what happens after that. Every sync re-checks each pin against the map it just built, and a pin pointing at a deleted path or a renamed symbol gets reported instead of quietly ignored. If a symbol was renamed, it looks through that file's own exports and asks whether buildGrap became buildGraph.

Then the ranking question, which is the one I expected to get. A pin only breaks a tie here. It cannot outrank a better match. We measured that on our own repo before turning it on: ten queries, three pins, two results moved by one position, top result never changed. Boosting the score was the easy version and it would have pushed correct answers down to promote a file somebody flagged last month for an unrelated reason.

Memory got the same treatment. It answered what happened, one event at a time, and that turned out not to be the question anyone had. There is now a diff that opens with the net move, plus three ways to find what you should delete: never recalled, low confidence, and stale since the code moved.

I ran a mapper over our own repository this week and counted something uncomfortable: how many of our decisions were ever written down anywhere a person could actually find them.

22 modules. 40 identifiable decisions. Of those 40:

4 were in a real document in the repo

3 were explained in a PR body

Hey Product Hunt

I built SecondOS because I kept re-explaining the same codebase to Cursor, then Claude Code, then Codex, in the same afternoon. Every new session, every new tool, back to zero. Your AI has no memory of your project, and you've probably just accepted that.

SecondOS fixes that. You sync your repo once. It builds a structure-aware map of your code (symbols, routes, a real call graph across TS, Go, Python, Rust, Java) plus a layer of durable memory: the decisions, the gotchas, the "this looks wrong but it's load-bearing" that never actually lives in the code. Then every AI tool reads the same thing over MCP. Cursor, Claude Code, Codex, ChatGPT. One memory.

Three things that make it different from bolting "memory" onto an agent: