Stop re-explaining your codebase to every AI tool

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:

→ It's living. A note is pinned to the exact code it's about. When that code changes, the note is flagged stale automatically, so your AI trusts fresh context and treats old notes as leads to verify. Chat-capture memory just rots quietly. This one tells you.

→ It can write itself. Opt in and it passively reads your local AI sessions, pulls the durable decisions, and records them scoped to the right project. No more playing secretary for your own tools.

→ It's honest about privacy. Code uploads as a map, the function bodies stay on your machine. Prose docs upload as full text (a real trade-off you control). And the client that runs on your machine is source-available, so you can read exactly what leaves it: github.com/Preatan/secondos-client

Free is genuinely free ($0, no card, local mode needs no login). Pro is $10.

I'll be in the comments all day. I'd love feedback on the drift and staleness model especially. And one honest question back at you: where should the line sit for what an AI is allowed to remember on its own vs ask you first?

— Oğuz (management@monafy.com · x.com/grbuzoguz)