Private by design
Redaction at ingest, pseudonymous authors, an encrypted database, air-gapped by default.
Voice of Customer without violating privacy
Understand feedback from every channel and language. Personal data is gone before anything is stored.
How it works
Section titled “How it works”- App Store
- Google Play
- Zendesk
- Intercom
- Gong
- GitHub
- Bluesky
- SQL
- Webhooks
- REST
- MCP
- Studio
- Agents (MCP)
- Slack
- Jira
- Linear
- Warehouse
Everything inside the dashed box runs on your machines. Read how obsei works for what each step does and who can see what.
Why obsei
Section titled “Why obsei”Bring your own
Your sources, your keys and any OpenAI-compatible model, from Ollama to Azure OpenAI.
AI-native
A read-only MCP server: agents answer with quotes and record ids, never identities.
Every language
Classified and quoted in its own language, grouped across languages into themes.
Start here
Section titled “Start here”QuickstartInstall, run the ten-language sample and ask your first question.
How it worksThe pipeline, the trust boundary and who sees what.
Sources and sinksEvery built-in connector and how to map your own data.
Privacy controlsRedaction by region, pseudonyms, erasure, retention and audit.
MCP and agentsConnect Claude, ChatGPT, Cursor and your own agents.
Server and accessWebhooks, scheduling, Studio, SSO and roles.