GitHub - anasmohiuddinsyed-bit/ai-fix: When a command fails, one word fixes it. AI-powered error fixer for your terminal. · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
anasmohiuddinsyed-bit
ai-fix
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>2 Commits<br>2 Commits
src/ai_fix
src/ai_fix
tests
tests
.gitignore
.gitignore
LAUNCH.md
LAUNCH.md
README.md
README.md
pyproject.toml
pyproject.toml
View all files
Repository files navigation
ai-fix
When a command fails, one word fixes it.
$ python app.py<br>ModuleNotFoundError: No module named 'uvicorn'
$ ai-fix<br>✗ Failed: No module named 'uvicorn'
Fix (high confidence): uvicorn is not installed in this environment.
→ pip install uvicorn
Apply fix? [Y/n]: y<br>Running: pip install uvicorn<br>✓ Done.
Re-running: python app.py<br>✓ Fixed! Command succeeded.
Install
pip install ai-fix
Set your API key:
export ANTHROPIC_API_KEY=sk-ant-... # Claude (recommended — fast + cheap)<br># or<br>export OPENAI_API_KEY=sk-... # OpenAI fallback
Done. That's it.
Usage
# Fix the last command that failed<br>ai-fix
# Run a command and fix it if it fails<br>ai-fix python app.py<br>ai-fix npm run build<br>ai-fix cargo build<br>ai-fix docker compose up
# Skip the confirmation prompt<br>ai-fix -y python app.py
# See what it would do without applying<br>ai-fix --dry-run python app.py
# Show full error output<br>ai-fix -v npm run build
How it works
Captures — re-runs your failed command and captures stdout + stderr
Sends — ships the error + system context to Claude (or GPT-4o-mini)
Gets back — structured fix commands with confidence score
Applies — runs the fix, then re-runs your original command to confirm
The AI sees: your command, the full error, your OS, Python/Node versions, and which project files exist (package.json, pyproject.toml, Cargo.toml, etc.). It gives back exactly the commands to run — no prose, no explanations you have to decode.
Examples
Python missing module
$ python server.py<br>ModuleNotFoundError: No module named 'fastapi'
$ ai-fix<br>Fix (high confidence): fastapi is not installed.<br>→ pip install fastapi
npm build failure
$ npm run build<br>sh: tsc: command not found
$ ai-fix<br>Fix (high confidence): TypeScript compiler not installed.<br>→ npm install --save-dev typescript<br>→ npx tsc
Permission denied
$ ./deploy.sh<br>bash: permission denied: ./deploy.sh
$ ai-fix<br>Fix (high confidence): Script is not executable.<br>→ chmod +x deploy.sh
Port already in use
$ python manage.py runserver<br>Error: That port is already in use.
$ ai-fix<br>Fix (medium confidence): Port 8000 is occupied by another process.<br>→ lsof -ti:8000 | xargs kill -9
Git push rejected
main (non-fast-forward)
$ ai-fix<br>Fix (high confidence): Remote has commits not in your local branch.<br>→ git pull --rebase origin main<br>→ git push">$ git push<br>! [rejected] main -> main (non-fast-forward)
$ ai-fix<br>Fix (high confidence): Remote has commits not in your local branch.<br>→ git pull --rebase origin main<br>→ git push
Docker not running
$ docker ps<br>Cannot connect to the Docker daemon. Is docker running?
$ ai-fix<br>Fix (high confidence): Docker daemon is not running.<br>→ open -a Docker
Why not just Google it?
You already know how to Google. But when you're deep in a build, context-switching to a browser, reading three Stack Overflow answers, and coming back costs minutes and breaks flow.
ai-fix keeps you in the terminal. One word. Done.
Confidence levels
Color<br>Meaning
🟢 high<br>AI is certain — common error, clear fix
🟡 medium<br>Likely fix, but depends on your setup
🔴 low<br>AI is guessing — review before applying
Shell support
Reads last command from:
zsh (~/.zsh_history)
bash (~/.bash_history)
fish (~/.local/share/fish/fish_history)
Cost
ai-fix uses Claude Haiku by default — the fastest and cheapest model. Each fix costs roughly $0.0003 (less than 1/10th of a cent). You'd need to run it 3,000 times to spend $1.
Privacy
Only sends: the failed command, its error output (truncated to 3000 chars), your OS, language versions,...