

gateway/middleware/ratelimit.go. Default: 100 req/min per API key, configurable per plan in config/plans.yaml1Switch between the best AI models with one click. No vendor lock-in.
Answers grounded in your internal docs, wikis, and knowledge bases.
Upload PDFs, spreadsheets, and documents. Get answers from any file.
Create visuals, diagrams, and graphics directly in the conversation.
Every claim linked back to its source document.
Pull in real-time information from the web when needed.
Multi-step analysis that synthesizes across many sources.
Link knowledge bases, drives, and wikis. One-click integrations for Confluence, Notion, Google Drive, and more.
Add users via SSO or email. Set permissions by team, role, or department.
Your team gets instant, cited answers from company knowledge — day one.
EU data residency with a full Data Processing Agreement. Your data stays in Europe.
Fine-grained permissions by team and role. Full usage dashboard for visibility.
Your data is never used to train AI models. Guaranteed by contract.
All uploaded files are processed in encrypted EU-based infrastructure. Data is used only to generate your response and is not stored beyond the session unless you choose to save it.
Conversation history is stored encrypted and accessible only to the user and authorized admins. You can delete conversations at any time.
No. Your data is never used to train or fine-tune any AI model. This is guaranteed by contract with all model providers.
We support Claude (Anthropic), GPT-4o (OpenAI), Gemini (Google), and open-source models like Llama. New models are added regularly.
Most teams are up and running in under an hour. Connect your knowledge sources, invite your team, and start chatting.