aicheck

aicheck

Catch AI-generated code issues before they catch you.

aicheck is a static analysis toolkit that detects common failure patterns in AI-generated Python code:

• Hallucinated imports — modules LLMs frequently invent (e.g. utils, helpers, misc)
• Dead code — unused variables, unreachable branches, code after return/raise
• Suspicious API usage — wrong method names for stdlib modules, open().read() patterns
• Confidence scoring — each file gets a 0–100 score based on findings severity

Installation

pip install aicheck

Quick Start

# Check a single file
aicheck check my_file.py

# Check an entire project
aicheck check src/

# JSON output for CI integration
aicheck check src/ --format json

Sample Output

[FAIL] src/suspicious.py  (score: 62.0)
    high  L1:0  [hallucinated_import] Potentially hallucinated module: 'utils'
           ↳ Verify 'utils' exists; check PyPI or project dependencies
  medium  L14:4  [unreachable_code] Unreachable branch: condition is always False
     low  L11:4  [dead_code] Possibly unused variable: 'unused_var'

Files: 1  Passed: 0  Failed: 1
Average confidence score: 62.0/100

CLI Reference

Score Interpretation

Development

git clone https://github.com/maheshmakvana/ai-check.git
cd ai-check
python -m venv venv && source venv/bin/activate
pip install -e ".[test]"
pytest tests/ -v
ruff check src/
mypy src/

License

MIT