VATES

VATES is embeddable B2B AI knowledge infrastructure. It stores an organisation's knowledge as structured, human-readable plain text and answers questions from it — from your team, your customers, or another AI. What makes VATES structurally different is how that knowledge is held. It remains readable text and is interpreted when a question is asked. There is no vector database, no embedding pipeline, and no re-ranking step. Edit an entry and the change takes effect from the very next answer — no re-indexing or rebuild step. Every answer can be traced back to the stored knowledge it came from. The source can be opened and checked, and deletions can be verified by eye. Administrative changes are recorded in a tamper-evident audit log built on a SHA-256 hash chain. The language of the knowledge base and the language of the conversation are independent. A knowledge base written in one language can answer a user in another without storing translated copies. The console, documentation, and public site are localised in 23 languages across 9 writing systems. Companies can use VATES as an embedded widget installed with one line of JavaScript, as a standalone chat page on their own domain, or through a developer API. For AI clients, VATES also exposes a remote MCP server with OAuth 2.1. MCP operations are idempotent by design. Billing is prepaid and usage-based. You deposit a balance and each request draws against it. The minimum top-up is USD 5.00, with no subscription, no monthly fixed fee, no minimum spend, and no cancellation fee.