I built an autonomous debugging tool for
Python developers.
What it does:
- Runs your pytest suite automatically
- Detects failures
- Applies fixes autonomously
- Validates every fix with return code
- Rolls back anything that makes it worse
- Shows exactly what changed
Demo: [paste YouTube link here]
Current capability:
Fixes dependency errors, import issues,
environment problems, and simple logic bugs.
Built with FastAPI, React, Supabase, Gemini API
Solo developer, ~3 weeks
I built a CLI that analyzes pytest failures and proposes fixes automatically. It shows you a diff before applying anything, so you stay in control.
Right now it handles common logic bugs - wrong operators, off-by-one errors, etc. Uses pattern analysis on test output plus an LLM fallback for edge cases.
The goal is to automate the test → fix → validate loop rather than just explaining errors. It re-runs the full suite after each fix to prevent regressions.
Looking for feedback on what kind of failures would be most useful to auto-fix, and beta testers to try it on real projects.
What it does: - Runs your pytest suite automatically - Detects failures - Applies fixes autonomously - Validates every fix with return code - Rolls back anything that makes it worse - Shows exactly what changed
Demo: [paste YouTube link here]
Current capability: Fixes dependency errors, import issues, environment problems, and simple logic bugs.
Built with FastAPI, React, Supabase, Gemini API Solo developer, ~3 weeks
Would love honest feedback.