charliegerard/safe-space
A GitHub Action that uses TensorFlow.js toxicity classification to detect and flag harmful comments in repositories.
Not currently ranked — collecting fresh signals.
star history
This GitHub Action integrates a pre-trained TensorFlow.js toxicity classifier to analyze comments on pull requests, issues, and PR reviews. When potentially toxic content is detected, it can automatically post a comment alerting the author so they can edit the content before it persists. The tool runs as a CI workflow step using the GitHub Actions framework and accepts configurable toxicity thresholds.
Frequently asked
- What is charliegerard/safe-space?
- A GitHub Action that uses TensorFlow.js toxicity classification to detect and flag harmful comments in repositories.
- Is safe-space open source?
- Yes — charliegerard/safe-space is open source, released under the GPL-3.0 license.
- What language is safe-space written in?
- charliegerard/safe-space is primarily written in JavaScript.
- How popular is safe-space?
- charliegerard/safe-space has 473 stars on GitHub.
- Where can I find safe-space?
- charliegerard/safe-space is on GitHub at https://github.com/charliegerard/safe-space.