vikasojha48/Multi-AI Code Quality Analyzer
Automated AI-powered code review for GitHub pull requests with inline comments
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| github-token | GitHub token for PR comments | yes | — |
| openai-api-key | OpenAI API key | no | — |
| anthropic-api-key | Anthropic (Claude) API key | no | — |
| grok-api-key | Grok (xAI) API key | no | — |
| gemini-api-key | Google Gemini API key | no | — |
| ollama-url | Ollama server URL (e.g., http://localhost:11434) | no | — |
| model | AI model to use (e.g., gpt-5.1, gpt-4o, claude-3-5-sonnet-20241022, gemini-1.5-pro) | no | gpt-5.1 |
| fail-on-critical | Fail the action if critical issues are found | no | false |
| config-path | Path to the configuration file | no | .github/ai-review-config.yml |
| language | Language for review comments (en, ru, es, de, zh, ja, fr, pt) | no | en |
| mode | Review mode: "pr" for pull request diff, "full" for entire repository | no | pr |
| paths | Paths to review in full mode (comma-separated, e.g., "src/,lib/") | no | src/ |
| output-type | Output type for full mode: "issue" creates GitHub issue, "comment" posts as PR comment, "summary" outputs to action summary | no | issue |
Outputs
| name | description |
|---|---|
| review-comment-id | ID of the review comment posted |
| issues-found | Number of issues found |
| critical-issues | Number of critical issues found |