Core principles
Built to be trustworthy, not just capable
Most AI products are built for engagement. OpenCouch is built for trust — with clear safety boundaries, user-controlled memory, and an architecture that can run entirely on your own infrastructure.
No data sold. No third-party training. Self-hostable so data never leaves your infrastructure if you choose.
01Crisis detection runs as a hard gate before every response — deterministic patterns plus an LLM classifier, always.
02OpenCouch is not a therapist. It says so clearly, in onboarding, in prompts, and in every crisis response.
03Web chat first, then voice, WhatsApp, Telegram, and SMS — built in order of what actually matters to reach people.
04Not MIT — intentionally. AGPL ensures that anyone who deploys a modified version must publish their changes. Safety features like the crisis gate cannot be silently stripped in a closed fork.
05