Add Appliance Auto Whisperer - Right to Repair

[stripathy1999]

Made-with: Cursor

Summary

Multi-agent right-to-repair system under openai-agent-sdk/Appliance Auto Whisperer/:

• Gemini Vision (via OpenAI SDK) identifies broken parts from photos
• Bright Data Web Unlocker scrapes prices from 6+ retailers (Amazon, eBay, RepairClinic, etc.)
• YouTube Data API v3 finds the best brand-specific repair tutorial
• Orchestrator coordinates 2 worker agents via REST fan-out (true parallel with asyncio.gather)
• Falls back to direct service calls if workers are unavailable

Type of Change

• New agent example
• Bug fix
• Documentation update
• Refactor / cleanup
• Other

Checklist

• I have starred this repository.
• I ran ruff check ..
• I ran ruff format ..
• I added/updated README.md for changed example(s).
• I added .env.example if environment variables are required.
• I added demo image/GIF (if applicable).
• I added agent profile link (if applicable).
• I updated CHANGELOG.md (required for non-doc changes).
• I verified paths/commands used in docs.

Related Issue

N/A

Notes for Reviewers

• SDK: OpenAI Python SDK — Gemini accessed via its OpenAI-compatible endpoint.
• Architecture: 3 uAgents (orchestrator + parts worker + tutorial worker) communicating via direct REST POST calls, avoiding the mailbox-poll deadlock inherent in send_and_receive.
• Docker: docker-compose --profile bureau up --build starts all 3 containers with healthcheck-gated orchestrator startup.
• Category: LLM, Multi-Agent, Integration | Difficulty: Advanced