Connect your data to your AI agents

Open source infrastructure that makes your existing databases AI-ready. Describe how you want agents to interact with your data, and get a full-featured engine to make it happen.

curl -fsSL /install | bash

The open source infrastructure you need.

Automatic REST API Generation

Define queries in a schema, get REST endpoints automatically.

MCP Tools for AI Assistants

Expose queries as MCP tools for AI assistants via JSON-RPC.

Auto-Generated OpenAPI Documentation

OpenAPI 3.0 specs and markdown docs generated for you.

Multi-Database Support

PostgreSQL, MySQL, and Redis support out of the box.

Built-in Input Validation

Automatic type checking for all query parameters.

LLM-Friendly Documentation

Generates llms.txt and agent skills for AI integration.

Stop doing it the hard way.

Without Hyperterse
  • × Build custom API endpoints for each query
  • × Write boilerplate validation and error handling
  • × Manually create OpenAPI documentation
  • × Build MCP tools from scratch for each agent
  • × Maintain llms.txt and agent skills manually
  • × Weeks of development and ongoing maintenance
With Hyperterse
  • ✓ Define queries once in a schema
  • ✓ Automatic input validation and type checking
  • ✓ OpenAPI specs generated automatically
  • ✓ MCP tools ready for any AI agent
  • ✓ llms.txt and agent skills auto-generated
  • ✓ Up and running in minutes
Learn more →

How it works

Input
Schema
Structured description of your data
→
Process
Hyperterse
Parser and runtime for your schema
→
Output
REST + MCP
Agent-ready tools and literature

Full-featured engine that allows agents to interact with your data.

No code required.

Frequently Asked Questions

+ What is Hyperterse?
Hyperterse is a high-performance runtime server that transforms database queries into RESTful API endpoints and MCP (Model Context Protocol) tools. It acts as a query gateway that lets you define queries in a schema and automatically generates APIs, documentation, and AI-ready tooling.
+ Is Hyperterse free?
Yes. Hyperterse is free and open source. You can self-host it on your own infrastructure at no cost. If you need any help, we offer enterprise support. Reach out to us at enterprise@hyperterse.ai
+ How do I define queries?
Queries are defined in a simple schema file. You specify the database connection, the SQL query, and input parameters with their types. Hyperterse handles the rest—generating endpoints, validating inputs, and creating documentation.
+ Which databases are supported?
Hyperterse supports PostgreSQL, MySQL, and Redis out of the box. Each database has its own connector, and you can configure multiple database connections in a single Hyperterse instance.
+ What is MCP and how does it work?
MCP (Model Context Protocol) is a standard for exposing tools to AI assistants and LLMs. Hyperterse automatically generates MCP-compatible tools for each query you define, allowing AI agents to execute database queries via JSON-RPC 2.0.
+ Is my database connection secure?
Yes. Connection strings and raw SQL are never exposed to clients. Hyperterse acts as a secure gateway. Clients only interact with the generated API endpoints, not the underlying database directly.
+ What documentation formats are generated?
Hyperterse auto-generates OpenAPI 3.0 specifications for your REST endpoints, markdown documentation for human readers, and llms.txt files with agent skills for AI integration.
+ Do I need to write any code?
No. Hyperterse is schema-driven. You write SQL queries in schema files, and Hyperterse generates everything else. No boilerplate code, no ORM setup, no route handlers.
+ Is Hyperterse an ORM?
No. Hyperterse does not abstract away SQL. You write raw SQL queries directly. It focuses solely on query execution and API exposure, not database abstraction or migrations.