Ask your documents
anything. See the source.
QueryLlama searches your organization's documents by keyword, by meaning, or both — and every result points back to the exact file and passage it came from. Strict per-org isolation, enforced at the database layer, not just in application code.
One organization can never see another's documents.
Every table carries an organization ID, and Postgres Row-Level Security policies enforce that a query can only return rows belonging to the requesting user's organization — at the database layer. An application bug can't leak across tenants, because the database itself won't return the rows.
What it does, what's built, and what's next.
Search, RAG, BYOLLM and RBAC — each one labeled honestly by build status.
Planned tiers — shaped by our design partners.
Pricing isn't final. This is the shape we're building toward; design partners get a say in what each tier includes before general availability.
Free
- Keyword + semantic search
- One workspace
- Community support
Pro
Planned default- Everything in Free
- Hybrid search
- RAG question-answering
Enterprise
- Everything in Pro
- Bring your own LLM
- SSO, full audit log, dedicated support
Help shape what ships.
We're onboarding a small number of design partners ahead of general availability.