Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/arthurpanhku/job-pilot.git
cd job-pilot/backend
python -m venv venv
source venv/bin/activate
pip install -r requirements.txtRegister it in Claude Code
claude mcp add -e "OPENAI_API_KEY=${OPENAI_API_KEY}" -e "SUPABASE_URL=${SUPABASE_URL}" job-pilot -- python /path/to/job-pilot/backend/app/main.pyReplace any placeholder paths in the command with the real path on your machine.
OPENAI_API_KEYSUPABASE_URL+ 1 optionalMake your agent remember this setup
job-pilot's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Agent-first design built on the Model Context Protocol
- Context-aware resume optimization for specific job descriptions
- Automated job searching with semantic filtering
- Stealth-mode application automation with human-like delays
- Integrated dashboard for tracking application status and history
Tools 3
search_jobsScrapes and filters job listings from platforms like LinkedIn and Indeed based on a semantic profile.optimize_resumeAnalyzes a master profile against a specific job description to generate a tailored resume.apply_to_jobAutomates the job application process using browser automation with human-like delays.Environment Variables
OPENAI_API_KEYrequiredAPI key for LLM-based resume optimization and analysis.ANTHROPIC_API_KEYAPI key for Anthropic models used in agentic workflows.SUPABASE_URLrequiredDatabase connection string for storing application history.Try it
Original README from arthurpanhku/job-pilot
JobPilot ✈️
Your Intelligent AI Agent for Career Success Automated Job Search, Resume Optimization, and Application Management
Features • Architecture • Getting Started • Roadmap
English | 中文 | 日本語 | 한국어 | Français | Deutsch
📖 Introduction
JobPilot is a next-generation career assistant powered by AI Agents and the Model Context Protocol (MCP). It acts as your personal recruiter, tirelessly searching for jobs on platforms like LinkedIn, optimizing your resume for specific job descriptions (JD), and even automating the application process.
Designed for the age of AI, JobPilot exposes a full MCP server, allowing you to connect it with your favorite AI assistants (like Claude Desktop, OpenClaw, or custom agents) to handle your job hunt autonomously.
<a href="https://glama.ai/mcp/servers/arthurpanhku/job-pilot"> </a>Why JobPilot? Instead of manually tweaking your CV for every application, let JobPilot's agents analyze the JD, rewrite your resume to highlight relevant skills, and submit the application for you—while you sleep.
✨ Features
🤖 MCP-Native Architecture
- Agent-First Design: Built from the ground up as a Model Context Protocol (MCP) server.
- Universal Compatibility: Connects seamlessly with any MCP-compliant client (Claude, IDEs, Agent frameworks).
📄 Intelligent Resume Engine
- Context-Aware Optimization: Analyzes your master profile against target JDs to generate hyper-personalized resumes.
- ATS Friendly: Ensures generated resumes are optimized for Applicant Tracking Systems.
🕵️ Automated Job Hunter
- Smart Search: Scrapes and filters job listings from LinkedIn and Indeed based on your semantic profile.
- Auto-Apply: Automated form filling with built-in stealth mode and anti-detection mechanisms (human-like delays, randomized user agents).
- Risk Reduction: "Safe Mode" with dry-run capability and manual confirmation steps to avoid account flags.
📊 Application Tracking
- Dashboard: Modern UI built with Shadcn components to visualize your application status, interview pipeline, and success rates.
- History: Keep a record of every tailored resume version sent to recruiters.
🛠️ Tech Stack
- Frontend:
- Next.js 14 (App Router)
- TypeScript
- Tailwind CSS & Lucide Icons
- Backend:
- FastAPI (Python)
- Pydantic
- MCP SDK (Python)
- Automation & AI:
- Playwright (Browser Automation)
- OpenAI / Anthropic APIs (LLM)
- Supabase (Database & Auth)
🚀 Getting Started
Prerequisites
- Node.js 18+
- Python 3.11+
- Git
Installation
Clone the repository
git clone https://github.com/yourusername/job-pilot.git cd job-pilotBackend Setup
cd backend python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate pip install -r requirements.txt # Start the API & MCP Server python app/main.pyFrontend Setup
cd frontend npm install # Start the UI npm run devAccess the App
- Frontend:
http://localhost:3000 - API Docs:
http://localhost:8000/docs
- Frontend:
🗺️ Roadmap
- Project Initialization & Architecture Design
- Phase 1: MCP Server Implementation & Basic Profile Management
- Phase 2: LinkedIn Scraper Integration & Job Matching
- Phase 3: Resume Optimization Pipeline (LLM)
- Phase 4: Automated Application via OpenClaw/Playwright
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
🌟 Star History
📄 License
This project is licensed