Code engine for AI agents claims major token savings

Gortex is a code- engine meant to help AI agents and understand large codebases with less repeated reading. It indexes code and exposes the results through a , an MCP server, and a .

It is described as working across multiple repositories by default and shipping as one static file for macOS, Linux, and Windows. It uses tree-sitter to parse 257 languages and grammars, then builds a of functions, classes, call chains, HTTP routes, and links between services.

It claims deeper code understanding for major languages such as Python, TypeScript, JavaScript, Go, Rust, Java, C, C++, PHP, C#, Swift, Ruby, and others. It offers 175 configurable MCP tools, works with 17 , and claims up to 50 times fewer tokens per response.

Key points

  • Gortex targets AI agents and IDEs that need to understand codebases.
  • It provides access through a , an MCP server, and a .
  • It supports multiple repositories and is described as a single static binary.
  • It parses 257 languages and builds a of code relationships.
  • It claims up to 50 times fewer tokens per response.
Read original