I did the comparison of two repository packaging tools Axleta Repository Packer and Gitingest by packing public repository of "https://github.com/expressjs/express" on both tools. Finally attached both output files to the Google Search AI online and asked to analyze both files to select which one is the best AI-friendly file to add LLMs prompt context.
As per the Google Search AI analysis, Axleta Repository Packer is the best tool to pack a GitHub repository for LLMs in a more AI-friendly format.
Here is the analysis generated by Google Search AI Mode
Head-to-Head Comparison: Axleta vs. Gitingest
| Evaluation Criteria | Axleta (File 1) | Gitingest (File 2) |
|---|---|---|
| LLM Parsing Accuracy |
Higher. Uses <file path="...">...</file> tags that modern LLMs are specifically trained to recognize as strict context boundaries. |
Moderate. Relies on === divider lines, which can collide with Markdown headers or ASCII banners inside source files. |
| Prompt Injection Defense |
Built-in. Includes a <packing_notes> block explicitly instructing the LLM to treat file contents as passive data. |
None. Lacks framing instructions, leaving the prompt more vulnerable to instructions hidden in code comments or READMEs. |
| Token Efficiency | More compact. Skips empty files in the body and uses brief XML tags, saving tokens on large repositories. |
Slightly bloated. Repeats 96 = characters per file and creates full header blocks for [Empty file] entries. |
| Version Traceability | Complete. Records the exact repository name, branch, commit hash, and file count at the top. | Minimal. Only displays the root directory name without branch or commit metadata. |
| Human Readability | Moderate. XML tags are easy to scan, though the directory list is unindented. |
High. The visual ASCII tree (├──, └──) is very easy for humans to read at a glance. |
Top comments (0)