Loading page
Loading page

AI
Turn any Git repository into one prompt-friendly text digest you can paste into an LLM.
Gitingest turns a Git repository into a single text digest built for LLM prompts. You give it a repository URL, and it returns a summary of the file tree, the size of the extract, a token count and the file contents in a format a model can read easily.
The project also ships a command-line tool, a Python package and browser extensions. This template runs the web server version. The server can expose Prometheus metrics, report errors to Sentry and store digests in S3, all turned on through settings.
It is for developers who use chat models to understand or change code. It helps when you want a model to see a whole small project at once rather than file by file.
Running your own Gitingest means repositories are cloned and processed on your server, not on a public service. That matters when you work with private code and tokens.
The trade-off is that large repositories take time, disk and memory to process, and the digest may exceed a model's context window. You keep the image updated, guard any tokens you add, and limit who can reach the app if you use it with private code.
Containers: elestio/gitingest:${SOFTWARE_VERSION_TAG}
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Gitingest, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Gitingest setup screen.