Context Ambulance

About

🚑 Stop wasting hours when the AI keeps apologizing, repeating broken code, or going in circles.

Context Ambulance scrapes your "poisoned" conversation, identifies what went wrong, and generates a clean rescue package you can paste into a fresh chat (or switch to Claude / Gemini) to continue productively.

🔥 THE PROBLEM
You know this nightmare:
• Hour 3: "Let me try a different approach…" (again)
• Hour 4: More apologies + the same broken fix
• Hour 5: You don't want to restart, but you're stuck

LLMs can become "context-poisoned" after repeated failed attempts. Starting fresh usually means losing progress. Until now.

✨ HOW IT WORKS (3 CLICKS)

Click the ambulance icon while on ChatGPT / Claude / Gemini

Auto-scrapes the conversation (no copy/paste)

Choose your action:
   🚑 Rescue — Download a clean .md package for a fresh LLM session
   🔄 Revival — Copy a reset prompt to paste in the same chat
   💾 Export — Save the full conversation as a clean .md file

Rescue packages include:
– Original goal (extracted)
– Primary blocker (root cause)
– Cleaned history (loops removed)
– Next-step recommendations

Then paste the rescue package into a new chat. Same context, none of the poison.

💾 NEW: EXPORT CONVERSATIONS
Switching LLM providers? Want to keep a conversation for your records? Export any chat from ChatGPT, Claude, or Gemini as a clean markdown file — no analysis, just a straight transcript. Files are named with the conversation title automatically.

🎯 WHAT GETS RESCUED
✅ Apology cascades
✅ Code churn / back-and-forth edits
✅ Repetitive errors
✅ Dead-end tangents
✅ Partial solutions buried in noise

🔒 PRIVACY FIRST
• No tracking, no account required
• Conversations are not stored on our servers
• Open source — audit the code on GitHub

🧰 OPTIONAL: PYTHON CLI
Power users can install the companion CLI for offline analysis, custom rules, and batch processing.

Open-source repo: github.com/leyiwu/context-ambulance
Chrome Web Store listing: (this page)