Third-party toolUpdated 2026.11.14

Gitingest: Inspect a Local Repository Before Sending It to AI

Run Gitingest 0.3.1 locally and inspect its summary, directory tree, and file contents. Verify exclusions and the error for an absent input directory.

Aaron recommends Open official GitHub

Gitingest returns a summary, directory tree, and file contents from a repository. Its 0.3.1 Python API processed a synthetic local directory in a network-disabled container, reporting two analyzed files and preserving the expected text and code. This test covers local preparation, with no GitHub account or hosted-service interaction.

For finer control over the packed scope, compare Repomix's file filters. For a few local text files, see files-to-prompt's output format.

Prepare a repository with known contents

Put README.md and sum.py in project/. Use Dispatch NOTE-31 leaves at 08:30. as the known sentence and return a + b as the code check. Add private.txt and debug.log as exclusion controls. A disposable fixture makes selection mistakes visible before you try a working repository.

Read all three return values

Install the pinned package in a Python 3.12 virtual environment and run the example below. The include patterns restrict file types; the exclude patterns explicitly identify unwanted material. Inspect summary and tree before using content as a model input.

These commands use a POSIX shell. The test ran in Linux; Windows shell behavior was not tested.

python -m pip install "gitingest==0.3.1"
python - <<'PY'
from gitingest import ingest
summary, tree, content = ingest("./project", include_patterns={"*.md", "*.py"}, exclude_patterns={"private.txt", "*.log"})
print(summary)
print(tree)
print(content)
PY

Observed outputs and failure

The summary reported Files analyzed: 2, and the tree contained README.md and sum.py. Content retained the sentence and addition function without either excluded record. Input hashes remained unchanged. An absent directory raised ValueError rather than returning a successful empty result. Automation should handle that exception separately from valid output.

Scope and selection

The three-part local API is useful when you want to assemble your own prompt or verify file coverage. The hosted service, remote cloning, and private repositories are described from official v0.3.1 material and the saved upstream snapshot; they were not locally tested. Large-repository performance and model answer quality remain unmeasured. Compare Repomix if you prefer one packaged document with explanatory scaffolding.

Official sources and test scope

Codex ran this synthetic-data test in a credential-free, non-root, network-disabled container. It is not a claim that the site owner tested it. Package version: 0.3.1; documentation snapshot: 4e259a02fe72.

Subscribe to AI tool picks and practical advice

Get worthwhile tool picks, test findings and important updates in your inbox.

Get a monthly-updated list of AI tools and Skills right away. We email when there are worthwhile tool picks, test findings or important updates. Unsubscribe anytime. Privacy

Almost done: check your inboxClick the button in the confirmation email and you will get the download link for the tool list. If you do not see it, check your spam or Promotions folder.

Or follow us on: