Analysis updated 2026-05-18
Automatically score the production risk of every pull request in a repository.
Block a pull request from merging if its risk score is above a chosen threshold.
Paste a code diff into the companion website to get a quick risk score without any setup.
Add an AI powered safety check to an existing GitHub Actions CI pipeline.
| blast-radar/blastradar-action | 00kaku/gallery-slider-block | 0xkinno/vellum | |
|---|---|---|---|
| Stars | 0 | — | 0 |
| Language | JavaScript | JavaScript | JavaScript |
| Last pushed | — | 2021-05-19 | — |
| Maintenance | — | Dormant | — |
| Setup difficulty | easy | easy | hard |
| Complexity | 2/5 | 2/5 | 4/5 |
| Audience | developer | general | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires an Anthropic API key stored as a repository secret, the README does not explain how the risk score is calculated internally.
BlastRadar is a GitHub Action, a small automated check that runs whenever someone opens a pull request on GitHub. It looks at the code changes in that pull request and gives them a risk score from 1 to 10, estimating how risky the change might be if it were released to production. If the score is too high, the check can block the pull request from being merged. Setting it up means adding a short configuration file to a repository's workflows folder that tells GitHub to run BlastRadar every time a pull request is opened. The action needs an Anthropic API key, stored as a secret in the repository settings, since it uses an AI model to analyze the code changes. There is also an optional setting called threshold, which defaults to 7, that controls the risk score at which the check fails. Once configured, the action produces two outputs for each pull request: the numeric risk score itself, and a one line verdict summarizing why that score was given. The project also has a companion website where anyone can paste in a code diff directly and get a risk score back in about ten seconds, without needing to set up the GitHub Action at all. The README for this project is fairly brief and does not go into detail about how the risk scoring itself works internally, what specific factors raise or lower a score, or what license the project is released under. The team behind it lists an email address for feedback.
A GitHub Action that automatically scores every pull request's risk from 1 to 10 using AI, and can block merges when a change looks too risky.
Mainly JavaScript. The stack also includes JavaScript, GitHub Actions, Anthropic API.
The README does not state a license, so usage terms are unclear.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.