Gitingest is a code ingestion tool that converts Git repositories into prompt-friendly text digests for large language models.
The tool solves the problem of preparing codebases for LLM consumption by extracting repository contents and formatting them optimally for AI prompts. It works by accepting a Git repository URL or local directory path and generating a structured text digest that includes the codebase alongside statistics about file structure, extract size, and token count. The approach is straightforward: replace 'hub' with 'ingest' in any GitHub URL to retrieve the corresponding digest, or use the tool programmatically as a Python package or command-line utility.
Developers should choose this tool when they need to feed codebase context to language models for code analysis, documentation generation, or AI-assisted development tasks. It suits projects of any size where understanding the full repository structure and contents is necessary for an LLM. The tool handles both public and private repositories, though private repository access requires a GitHub Personal Access Token. Installation is available through standard Python package management, and the tool requires Python 3.8 or later.
The project maintains active continuous integration with automated testing on the main branch. Code quality is enforced through a linter, and the project holds a security scorecard rating. The tool is distributed as a package available through standard package repositories and is also offered as browser extensions for Chrome and Firefox, indicating ongoing effort to expand accessibility beyond command-line and programmatic interfaces.
