TraceFlow
AI-powered crash analysis and one-click fixes for Python — right inside VS Code.
TraceFlow watches your Python script run, catches the exact moment it crashes, and uses AI to explain why it crashed and how to fix it — then lets you apply that fix with a single click, without ever leaving your editor.
📺 Demo
▶ Watch the full video demo
✨ Features
- Run with Trace — execute your Python file with a single click and let TraceFlow watch for crashes in real time.
- Instant crash highlighting — the exact line that caused the error is highlighted directly in your code.
- AI-powered root cause analysis — a side panel streams a clear, human-readable explanation of what went wrong, written specifically for your crash and your code.
- One-click Apply Fix — when TraceFlow proposes a fix, apply it directly to your file and watch the change highlighted in green.
- No bug? No problem — if your script runs cleanly, TraceFlow tells you so instead of leaving you guessing.
- Built-in authentication — sign in with email/password or GitHub, right from the editor.
🚀 How It Works
- Open a saved
.py file.
- Click the Run button in the editor toolbar (or use the TraceFlow status bar item).
- If your script crashes, TraceFlow:
- Highlights the offending line in red.
- Opens the TraceFlow Analysis panel beside your editor.
- Streams an AI explanation of the root cause as it's generated.
- Shows an Apply Fix button if a corrected version of the code is available.
- Click Apply Fix to patch your file automatically — the updated lines are briefly highlighted in green so you can see exactly what changed.
- If your script runs without errors, TraceFlow simply lets you know everything looks good.
🛠️ Getting Started
- Install the TraceFlow extension from the VS Code Marketplace.
- Open any saved
.py file.
- Click Run (or run the TraceFlow: Run with Trace command from the Command Palette).
- On first use, you'll be prompted to sign in or create a free account.
- That's it — TraceFlow takes care of the rest.
Note: TraceFlow currently supports Python files only.
⌨️ Commands
| Command |
Description |
TraceFlow: Run with Trace |
Runs the active Python file and analyzes any crash that occurs. |
TraceFlow: Sign In |
Sign in to your TraceFlow account (email/password or GitHub). |
TraceFlow: Sign Out |
Sign out and clear your stored credentials. |
TraceFlow: Reset Password |
Start the password reset flow for your account. |
All commands are also available from the Command Palette (Ctrl+Shift+P / Cmd+Shift+P).
📦 Requirements
- Python must be installed and available on your system
PATH.
- An active internet connection (AI analysis runs on TraceFlow's servers).
- A free TraceFlow account — sign up takes a few seconds from within the extension.
💎 Plans
TraceFlow's free plan includes a daily allowance of AI-powered crash analyses — plenty for everyday debugging.
If you hit your daily limit, TraceFlow will let you know and offer the option to upgrade to TraceFlow Pro for unlimited analyses.
🔒 Privacy
When a crash occurs, TraceFlow sends only the relevant crash details (traceback, surrounding code, and variable state at the time of the error) to TraceFlow's backend for AI analysis. Your full codebase is never uploaded — only the context needed to diagnose the specific error.
🐞 Known Limitations
- Python only (for now — more languages may be supported in future releases).
- Requires the file to be saved before running.
- Requires an internet connection; AI analysis will not work offline.
💬 Feedback & Support
Found a bug, have a feature request, or just want to say hi? Reach out via traceflow.pasly.co — feedback directly shapes what gets built next.
📋 Release Notes
See CHANGELOG.md for details on each release.
