GitHub - Kirill89/reviewcerberus: AI-powered code review tool that analyzes git branch differences and generates comprehensive review reports. Supports AWS Bedrock and Anthropic API. Features automated analysis of logic, security, performance, and code quality with smart token efficiency through prompt caching.

docker run --rm -it -v $(pwd):/repo \
  -e MODEL_PROVIDER=anthropic \
  -e ANTHROPIC_API_KEY=sk-ant-your-api-key \
  kirill89/reviewcerberus:latest \
  --repo-path /repo --output /repo/review.md

name: Code Review

on:
  pull_request:
    types: [opened, synchronize]

jobs:
  review:
    runs-on: ubuntu-latest
    permissions:
      contents: write
      pull-requests: write

    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - uses: Kirill89/reviewcerberus/action@v1
        with:
          model_provider: anthropic
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

# Run code review
poetry run reviewcerberus

# Custom target branch
poetry run reviewcerberus --target-branch develop

# Custom output location
poetry run reviewcerberus --output /path/to/review.md
poetry run reviewcerberus --output /path/to/dir/  # Auto-generates filename

# Output as JSON instead of markdown
poetry run reviewcerberus --json

# Different repository
poetry run reviewcerberus --repo-path /path/to/repo

# Add custom review guidelines
poetry run reviewcerberus --instructions guidelines.md

# Enable verification mode (experimental)
poetry run reviewcerberus --verify

# Enable SAST pre-scan (experimental)
poetry run reviewcerberus --sast

# Full review with custom guidelines
poetry run reviewcerberus --target-branch main \
  --output review.md --instructions guidelines.md

# Review a different repo
poetry run reviewcerberus --repo-path /other/repo

Repository: /path/to/repo
Current branch: feature-branch
Target branch: main

Found 3 changed files:
  - src/main.py (modified)
  - src/utils.py (modified)
  - tests/test_main.py (added)

Starting code review...

🤔 Thinking... ⏱️  3.0s
🔧 read_file_part: src/main.py

✓ Review completed: review_feature-branch.md

Token Usage:
  Input tokens:  6,856
  Output tokens: 1,989
  Total tokens:  8,597

MODEL_PROVIDER=bedrock  # or "anthropic", "ollama", "moonshot" (default: bedrock)

AWS_ACCESS_KEY_ID=your_key
AWS_SECRET_ACCESS_KEY=your_secret
AWS_REGION_NAME=us-east-1
MODEL_NAME=us.anthropic.claude-opus-4-5-20251101-v1:0  # optional

docker run --rm -it -v $(pwd):/repo \
  -e AWS_ACCESS_KEY_ID=your_key \
  -e AWS_SECRET_ACCESS_KEY=your_secret \
  -e AWS_REGION_NAME=us-east-1 \
  kirill89/reviewcerberus:latest \
  --repo-path /repo --output /repo/review.md

ANTHROPIC_API_KEY=sk-ant-your-api-key-here
MODEL_NAME=claude-opus-4-5-20251101  # optional

MODEL_PROVIDER=ollama
OLLAMA_BASE_URL=http://localhost:11434  # optional, default
MODEL_NAME=deepseek-v3.1:671b-cloud     # optional

# Assumes Ollama running on host machine
docker run --rm -it -v $(pwd):/repo \
  -e MODEL_PROVIDER=ollama \
  -e OLLAMA_BASE_URL=http://host.docker.internal:11434 \
  kirill89/reviewcerberus:latest \
  --repo-path /repo --output /repo/review.md

MODEL_PROVIDER=moonshot
MOONSHOT_API_KEY=sk-your-api-key-here
MOONSHOT_API_BASE=https://api.moonshot.ai/v1  # optional, default
MODEL_NAME=kimi-k2.5                          # optional

MAX_OUTPUT_TOKENS=10000     # Maximum tokens in response
TOOL_CALL_LIMIT=100         # Maximum tool calls before forcing output
VERIFY_MODEL_NAME=...       # Model for verification (defaults to MODEL_NAME)

- uses: Kirill89/reviewcerberus/action@v1
  with:
    model_provider: anthropic
    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
    verify: "true"
    min_confidence: "7"

- uses: Kirill89/reviewcerberus/action@v1
  with:
    model_provider: anthropic
    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
    sast: "true"

- uses: Kirill89/reviewcerberus/action@v1
  with:
    model_provider: anthropic
    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
    fail_on: "high"

- uses: Kirill89/reviewcerberus/action@v1
  with:
    model_provider: bedrock
    aws_access_key_id: ${{ secrets.AWS_ACCESS_KEY_ID }}
    aws_secret_access_key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
    aws_region_name: us-east-1

# Clone and install
git clone <repo-url>
poetry install

# Configure credentials
cp .env.example .env
# Edit .env with your provider credentials

make test
# or
poetry run pytest -v

make lint     # Check with mypy, isort, black, mdformat
make format   # Auto-format with isort and black

make docker-build           # Build locally
make docker-build-push      # Build and push (multi-platform)

├── src/                             # Python CLI
│   ├── config.py                    # Configuration
│   ├── main.py                      # CLI entry point
│   └── agent/
│       ├── agent.py                 # Agent setup
│       ├── model.py                 # Model initialization
│       ├── runner.py                # Review execution
│       ├── prompts/                 # Review prompts
│       ├── schema.py                # Data models (structured output)
│       ├── git_utils/               # Git operations
│       ├── formatting/              # Context and output rendering
│       ├── verification/            # Chain-of-Verification pipeline
│       ├── progress_callback_handler.py
│       └── tools/                   # 3 review tools
│
└── action/                          # GitHub Action (TypeScript)
    ├── action.yml                   # Action definition
    ├── src/                         # Action source code
    └── dist/                        # Bundled action