sukhrobnurali/Multi-Agent PR Reviewer
Specialist agents (security, performance, tests, quality) review a PR in parallel via LangGraph.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| github_token | GitHub token used to fetch the PR diff and post the review comment. | no | ${{ github.token }} |
| provider | LLM provider (openai or anthropic). Overrides .pr-review.yml. | no | — |
| model | Default model id (e.g. gpt-4o-mini, claude-haiku-4). Overrides .pr-review.yml. | no | — |
| api_key | LLM API key. Falls back to OPENAI_API_KEY / ANTHROPIC_API_KEY env. | no | — |
| config_path | Path to .pr-review.yml inside the checkout. Defaults to ./.pr-review.yml. | no | — |
| only | Comma-separated subset of agents to run (e.g. "security,quality"). | no | — |
| dry_run | If true, log the review comment instead of posting it. | no | false |
| cache_dir | Path to a directory to use as on-disk agent-result cache. If unset, caching is off. | no | — |
Outputs
no outputs