Open Source · Rust · Fast

High-performance repository context generator for LLMs

Transform codebases into optimized formats for Claude, GPT-4, Gemini, Llama, Mistral, DeepSeek, Qwen, and other large language models. Built in Rust for maximum performance.

Documentation View on GitHub

Installation

Cargo

cargo install infiniloom

Homebrew

brew tap Topos-Labs/infiniloom && brew install --cask infiniloom

pip

pip install infiniloom

npm

npm install -g infiniloom

Features

21 Languages

Tree-sitter based parsing for accurate symbol extraction across all major programming languages.

PageRank Symbols

Intelligent symbol ranking using PageRank algorithm to identify the most important code structures.

Secret Detection

Automatic detection and redaction of API keys, passwords, and other sensitive information.

Multi-Format Output

Export to XML, Markdown, JSON, YAML, TOON, or Plain text with model-specific optimizations.

Token Management

Built-in token counting and budget management for optimal context window usage.

Language Bindings

Native Python and Node.js bindings for seamless integration into your applications.

Quick Start

Terminal

# Pack a repository for Claude
infiniloom pack ./my-project --model claude --output context.xml

# Generate a repository map
infiniloom map ./my-project

# Scan for secrets before sharing
infiniloom scan ./my-project

# Analyze impact of changes
infiniloom impact ./my-project --files src/main.rs
                    

Supported Languages

Ready to get started?

Read the documentation or dive straight into the code on GitHub.

Read the Docs GitHub