ableinc/git2txt
Convert all files in git repository to .txt files. Useful for training LLMs on your codebase.
This tool helps developers transform their entire codebase, stored in a Git repository, into a collection of plain text files. It processes all code, documentation, and configuration files, excluding specified types, to prepare a clean dataset. The output is a directory of `.txt` files, ready for use by large language models. This is ideal for developers or machine learning engineers looking to fine-tune AI models on their specific code patterns and project knowledge.
No commits in the last 6 months.
Use this if you need to quickly extract all relevant text content from a Git repository to create a dataset for training a large language model on your codebase.
Not ideal if you need to analyze specific code characteristics or perform complex static analysis, as it only converts files to plain text without preserving rich metadata or code structure.
Stars
43
Forks
20
Language
Python
License
—
Category
Last pushed
Dec 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ableinc/git2txt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cyanheads/repo-map
repo-map generates LLM-enhanced summaries and analysis of software repositories, providing...
kirill-markin/repo-to-text
Convert a repository structure and its contents into a single text file, including the tree...
TonyStef/Grov
Grov automatically captures the context from your private AI sessions and syncs it to a shared...
zebangeth/DirPrint
Print/export your project's directory structure and code | Simplify your code sharing with...
abinthomasonline/repo2txt
Web-based tool converts GitHub repository contents into a single formatted text file