ix-infrastructure/Ix

What it solves

Ix addresses the difficulty of understanding large, complex codebases. Instead of relying on simple text searches (grepping) or pasting entire files into an AI prompt—which is expensive and often exceeds context limits—Ix creates a structured, persistent map of a repository's architecture.

How it works

Ix uses tree-sitter to parse a repository and extract symbols, calls, and imports. This data is stored as a graph in a local backend (ArangoDB and a memory layer running in Docker). Users and AI agents can then query this graph via a CLI, a visualizer called Compass, or an MCP (Model Context Protocol) server that allows AI clients like Claude Code, Cursor, and VS Code to navigate the codebase structure directly.

Who it’s for

It is designed for developers and AI coding agents who need to understand the relationships, dependencies, and impact of changes within a codebase across 27 supported languages.

Highlights

• Persistent System Graph: Maps symbols and relationships once and remembers them between sessions.
• Structural Querying: Provides commands to trace flows, explain symbols, and analyze the "blast radius" (impact) of changes.
• ** uma token efficiency**: Reduces token usage by 30-99.7% by providing bounded structural slices instead of full files to LLMs.
• Broad Language Support: Supports 27 languages, including C++, Python, Java, and Rust, as well as CUDA kernels.
• MCP Integration: Native support for the Model Context Protocol, allowing seamless integration with modern AI IDEs and agents.