Conduct in-depth interviews at scale using AI interviewers that adapt to responses. Open-source platform with study management, real-time synthesis, and one-click deployment.
OpenInterviewer is an open-source platform for conducting qualitative research interviews at scale. Instead of scheduling dozens of hour-long interviews, you design your study and share a link — participants engage with an AI interviewer that adapts based on their responses.
This is not a replacement for human interviews. AI interviews generate different data than human-conducted interviews. They’re a complementary method — useful for exploratory research, pilot studies, scaling data collection, and reaching participants across time zones. The platform is best understood as extending your research reach, not substituting your interpretive presence.
Conversation — Natural dialogue with an AI interviewer that adapts to responses
Demographics — Collected conversationally, not as a separate form
New to the platform? After deploying, click the “Load Demo” button on the My Studies page to explore with pre-built sample data — three complete interviews with full synthesis, so you can see the entire workflow before creating your own study.
For analytical operations like synthesis, the platform can auto-upgrade to premium models with extended thinking enabled — producing richer thematic analysis without slowing down the interview itself.
Operation
Reasoning
Model Used
Interview responses
OFF
Your selected model
Greeting generation
OFF
Your selected model
Per-interview synthesis
ON
Auto-upgraded (Gemini 3 Pro / Claude Opus)
Aggregate synthesis
ON
Auto-upgraded
Follow-up study generation
ON
Auto-upgraded
Each study can override this behavior: Automatic (recommended default), Always enabled (slower interviews but deeper responses), or Always disabled (faster, uses your selected model throughout). Keep in mind that auto-upgraded synthesis uses premium models — monitor costs if running many interviews.
When generating participant links, you can set expiration windows (7 days, 30 days, 90 days, or never) and toggle link access on or off from the study detail page. This is useful for closing data collection on a schedule, pausing a study, or revoking links if they’ve been shared beyond your intended sample.
The fastest path is one-click Vercel deployment — click the button below, set two environment variables, and you’re live in about two minutes.For local development:
Copy
git clone https://github.com/linxule/openinterviewer.gitcd openinterviewerbun installcp .env.example .env.local# Edit .env.local with your API keysbun run dev
Vercel KV credentials (KV_REST_API_URL, KV_REST_API_TOKEN, etc.) are configured automatically when you connect an Upstash Redis store through the Vercel dashboard.
