PR Checker AI 💚
An intelligent pull request review tool that leverages both OpenAI and Anthropic AI models to provide comprehensive code reviews directly on your GitHub pull requests.
Features
- Dual AI Analysis: Get reviews from both OpenAI GPT and Anthropic Claude models for comprehensive feedback
- Automated PR Comments: Automatically posts review results as comments on your GitHub pull requests
- Rich Console Output: Beautiful terminal output with tables and markdown rendering
- Flexible Model Selection: Choose specific models from OpenAI and Anthropic
- GitHub CLI Integration: Uses GitHub CLI for seamless PR interaction
Prerequisites
Before using PR Checker AI, ensure you have:
- GitHub CLI (
gh) installed and authenticated - OpenAI API Key - Set as
OPENAI_API_KEYenvironment variable - Anthropic API Key - Set as
ANTHROPIC_API_KEYenvironment variable
Installation
- Install
pr-checker-ai:
pip install pr-checker-ai
- Set up your API keys:
export OPENAI_API_KEY="your-openai-api-key"
export ANTHROPIC_API_KEY="your-anthropic-api-key"
- Ensure GitHub CLI is authenticated:
gh auth login
Usage
Basic Usage
Review a pull request (flag -p, --pr) using default models (gpt-4.1 for OpenAI and claude-sonnet-4-0 for Anthropic):
pr-checker-cli -p 123
Advanced Usage
Specify custom models for both providers using the flags:
-o, --openai: OpenAI model to use (default: "gpt-4.1")-a, --anthropic: Anthropic model to use (default: "claude-sonnet-4-0")
pr-checker-cli -p 456 -o "gpt-5" -a "claude-3-7-sonnet-latest"
How It Works
- Fetches PR Details: Uses GitHub CLI to collect general PR information and diff changes
- AI Analysis: Sends PR details to both OpenAI and Anthropic models for review
- Processes Responses: Filters and formats responses from both AI providers
- Posts Comment: Creates a formatted comment on the PR with both reviews
- Console Output: Displays results in a beautiful table format in your terminal
Output Format
The tool generates a structured comment on your PR containing:
- OpenAI Review: Analysis from the specified OpenAI model
- Anthropic Review: Analysis from the specified Anthropic model
- Approval Status: Each AI provides an approve/not approve recommendation
- Automated Footer: Indicates the comment was generated by PR Checker AI
Contributing
We welcome contributions! Please read our Contributing Guide to get started.
License
This project is licensed under the MIT License
Metadata
Release files for pr-checker-ai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| pr_checker_ai-0.1.0.tar.gz | 25.4 kB | Without provenance | Details for pr_checker_ai-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| pr_checker_ai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for pr_checker_ai-0.1.0-py3-none-any.whl |
Total release size: 31.3 kB
Release files / pr_checker_ai-0.1.0.tar.gz
| Download URL | pr_checker_ai-0.1.0.tar.gz |
|---|---|
| Size | 25.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
94b754bec5f03034d3f79d89aa54c179d5cfe6d32bbb379b171cb752c46d7712
|
|
BLAKE2b-256 checksum How to use checksums |
0eb93eb435c99158f66c533ed450965b2eff8a92499ba3b8399930a69d69c005
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.6
|
Release files / pr_checker_ai-0.1.0-py3-none-any.whl
| Download URL | pr_checker_ai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 6.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f5909c951fed445190de40285ac3b4c2440c801cdc658dc5aaad5118650cb80f
|
|
BLAKE2b-256 checksum How to use checksums |
3d250766153173d1d47cc5b63d3ad5a39b331a21e7bb8c56618f35705f03ccd5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.6
|
Security for pr-checker-ai 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.