740+ job listings evaluated · 100+ personalized CVs · 1 dream role landed — now 100% free and local
OpenCareer is a free, open-source fork of Career-Ops that replaces Claude Code with OpenCode and integrates local LLMs via Ollama. It turns any AI coding CLI into a full job search command center — with zero API costs and complete privacy.
Instead of manually tracking applications in a spreadsheet, you get an AI-powered pipeline that:
- Evaluates offers with a structured A-F scoring system (10 weighted dimensions)
- Generates tailored PDFs — ATS-optimized CVs customized per job description
- Scans portals automatically (Greenhouse, Ashby, Lever, company pages) using free web search
- Processes in batch — evaluate multiple offers with parallel sub-agents
- Tracks everything in a single source of truth with integrity checks
Important: This is NOT a spray-and-pray tool. OpenCareer is a filter — it helps you find the few offers worth your time out of hundreds. The system strongly recommends against applying to anything scoring below 4.0/5. Your time is valuable, and so is the recruiter's. Always review before submitting.
OpenCareer is agentic: OpenCode navigates career pages with Playwright, evaluates fit by reasoning about your CV vs the job description (not keyword matching), and adapts your resume per listing — all powered by free, local models like Gemma, Phi, and Qwen.
Heads up: the first evaluations won't be great. The system doesn't know you yet. Feed it context — your CV, your career story, your proof points, your preferences, what you're good at, what you want to avoid. The more you nurture it, the better it gets. Think of it as onboarding a new recruiter: the first week they need to learn about you, then they become invaluable.
Built by someone who used the original system to evaluate 740+ job offers, generate 100+ tailored CVs, and land a Head of Applied AI role — now made free and private for everyone. Read the full case study.
| Feature | Original Career-Ops | OpenCareer |
|---|---|---|
| AI Agent | Claude Code (paid subscription) | OpenCode (free, open-source) |
| LLM | Claude (cloud-based) | Local models via Ollama (Gemma, Phi, Qwen, etc.) |
| Web Search | Claude's built-in tools | Open WebSearch MCP (free, unlimited, DuckDuckGo) |
| Cost | ~$20+/month | $0 |
| Privacy | Data sent to Anthropic | Everything stays on your machine |
| Customization | Full control via modes | Same, plus ability to swap models freely |
| Feature | Description |
|---|---|
| Auto-Pipeline | Paste a URL, get a full evaluation + PDF + tracker entry |
| 6-Block Evaluation | Role summary, CV match, level strategy, comp research, personalization, interview prep (STAR+R) |
| Interview Story Bank | Accumulates STAR+Reflection stories across evaluations — 5-10 master stories that answer any behavioral question |
| Negotiation Scripts | Salary negotiation frameworks, geographic discount pushback, competing offer leverage |
| ATS PDF Generation | Keyword-injected CVs with Space Grotesk + DM Sans design |
| Portal Scanner | 45+ companies pre-configured (Anthropic, OpenAI, ElevenLabs, Retool, n8n...) + custom queries across Ashby, Greenhouse, Lever, Wellfound |
| Batch Processing | Parallel evaluation with opencode -p workers |
| Dashboard TUI | Terminal UI to browse, filter, and sort your pipeline |
| Human-in-the-Loop | AI evaluates and recommends, you decide and act. The system never submits an application — you always have the final call |
| Pipeline Integrity | Automated merge, dedup, status normalization, health checks |
| 100% Local & Free | No API keys required. All LLM inference runs on your machine via Ollama. Web search uses open-source MCP. |
# 1. Clone and install
git clone https://github.com/[your-username]/opencareer.git
cd opencareer && npm install
npx playwright install chromium # Required for PDF generation
# 2. Check setup
npm run doctor # Validates all prerequisites
# 3. Configure
cp config/profile.example.yml config/profile.yml # Edit with your details
cp templates/portals.example.yml portals.yml # Customize companies
# 4. Add your CV
# Create cv.md in the project root with your CV in markdown
# 5. Set up local LLM (Ollama)
ollama pull phi3:mini # Recommended for 8GB RAM
# Or: ollama pull qwen2.5:3b # Better reasoning
# Or: ollama pull gemma3:4b # Google's latest
# 6. Set environment variables (Windows CMD)
set OPENAI_API_KEY=ollama
set OPENAI_BASE_URL=http://localhost:11434/v1
set OPENAI_MODEL=phi3:mini
# 7. Personalize with OpenCode
opencode # Open OpenCode in this directory
# Then ask OpenCode to adapt the system to you:
# "Change the archetypes to backend engineering roles"
# "Translate the modes to English"
# "Add these 5 companies to portals.yml"
# "Update my profile with this CV I'm pasting"
# 8. Start using
# Paste a job URL or run /career-opsThe system is designed to be customized by the AI itself. Modes, archetypes, scoring weights, negotiation scripts — just ask OpenCode to change them. It reads the same files it uses, so it knows exactly what to edit.
See docs/SETUP.md for the full setup guide.
Career-ops is a single slash command with multiple modes:
/open-career-ops → Show all available commands
/open-career-ops {paste a JD} → Full auto-pipeline (evaluate + PDF + tracker)
/open-career-ops scan → Scan portals for new offers
/open-career-ops pdf → Generate ATS-optimized CV
/open-career-ops batch → Batch evaluate multiple offers
/open-career-ops tracker → View application status
/open-career-ops apply → Fill application forms with AI
/open-career-ops pipeline → Process pending URLs
/open-career-ops contacto → LinkedIn outreach message
/open-career-ops deep → Deep company research
/open-career-ops training → Evaluate a course/cert
/open-career-ops project → Evaluate a portfolio project
Or just paste a job URL or description directly — open-career-ops auto-detects it and runs the full pipeline.
You paste a job URL or description
│
▼
┌──────────────────┐
│ Archetype │ Classifies: LLMOps / Agentic / PM / SA / FDE / Transformation
│ Detection │
└────────┬─────────┘
│
┌────────▼─────────┐
│ A-F Evaluation │ Match, gaps, comp research, STAR stories
│ (reads cv.md) │
└────────┬─────────┘
│
┌────┼────┐
▼ ▼ ▼
Report PDF Tracker
.md .pdf .tsv
The scanner comes with 45+ companies ready to scan and 19 search queries across major job boards. Copy templates/portals.example.yml to portals.yml and add your own:
AI Labs: Anthropic, OpenAI, Mistral, Cohere, LangChain, Pinecone
Voice AI: ElevenLabs, PolyAI, Parloa, Hume AI, Deepgram, Vapi, Bland AI
AI Platforms: Retool, Airtable, Vercel, Temporal, Glean, Arize AI
Contact Center: Ada, LivePerson, Sierra, Decagon, Talkdesk, Genesys
Enterprise: Salesforce, Twilio, Gong, Dialpad
LLMOps: Langfuse, Weights & Biases, Lindy, Cognigy, Speechmatics
Automation: n8n, Zapier, Make.com
European: Factorial, Attio, Tinybird, Clarity AI, Travelperk
Job boards searched: Ashby, Greenhouse, Lever, Wellfound, Workable, RemoteFront
The built-in terminal dashboard lets you browse your pipeline visually:
cd dashboard
go build -o career-dashboard .
./career-dashboard --path ..Features: 6 filter tabs, 4 sort modes, grouped/flat view, lazy-loaded previews, inline status changes.
open-career-ops/
├── CLAUDE.md # Agent instructions
├── cv.md # Your CV (create this)
├── article-digest.md # Your proof points (optional)
├── config/
│ └── profile.example.yml # Template for your profile
├── modes/ # 14 skill modes
│ ├── _shared.md # Shared context (customize this)
│ ├── oferta.md # Single evaluation
│ ├── pdf.md # PDF generation
│ ├── scan.md # Portal scanner
│ ├── batch.md # Batch processing
│ └── ...
├── templates/
│ ├── cv-template.html # ATS-optimized CV template
│ ├── portals.example.yml # Scanner config template
│ └── states.yml # Canonical statuses
├── batch/
│ ├── batch-prompt.md # Self-contained worker prompt
│ └── batch-runner.sh # Orchestrator script
├── dashboard/ # Go TUI pipeline viewer
├── data/ # Your tracking data (gitignored)
├── reports/ # Evaluation reports (gitignored)
├── output/ # Generated PDFs (gitignored)
├── fonts/ # Space Grotesk + DM Sans
├── docs/ # Setup, customization, architecture
└── examples/ # Sample CV, report, proof points
| Component | Technology |
|---|---|
| Agent | OpenCode with custom skills and modes |
| LLM | Local models via Ollama (Phi, Qwen, Gemma, etc.) |
| Playwright + HTML template | |
| Scanner | Playwright + Greenhouse API + open-websearch MCP (DuckDuckGo) |
| Dashboard | Go + Bubble Tea + Lipgloss (Catppuccin Mocha theme) |
| Data | Markdown tables + YAML config + TSV batch files |
The open-websearch MCP server is an open-source Model Context Protocol (MCP) server that provides free, unlimited web search capabilities to AI agents like OpenCode. It acts as a bridge between OpenCode and public search engines (DuckDuckGo, Bing, etc.), allowing the AI to perform web searches without requiring paid API keys or hitting rate limits.
| Feature | Description |
|---|---|
| 100% Free | No API keys required; uses public search engines |
| No Rate Limits | Unlimited searches via DuckDuckGo |
| Privacy-First | All searches run locally; no third-party tracking |
| Multiple Engines | Supports DuckDuckGo, Bing, Google (with API key) |
| MCP Compatible | Works with OpenCode, Claude Desktop, and other MCP clients |
The original Career-Ops relied on Claude Code's built-in web search, which is tied to a paid subscription. OpenCareer replaces this with open-websearch MCP, ensuring:
- Zero API costs for job scanning
- No rate limits when scanning dozens of portals
- Complete privacy (searches don't leave your machine beyond the search engine)
The server exposes an MCP-compatible endpoint that OpenCode connects to. When the AI needs to search the web, it calls the server's search tool, which queries the configured search engine and returns structured results.
- Node.js 18+ (required for
npxto run the server) - OpenCode CLI installed
- Terminal access (Command Prompt, PowerShell, or terminal of choice)
This runs the server directly without global installation.
# Start the server with DuckDuckGo as default engine
npx -y open-websearch@latest
# Windows Command Prompt
set DEFAULT_SEARCH_ENGINE=duckduckgo && npx -y open-websearch@latest
# Windows PowerShell
$env:DEFAULT_SEARCH_ENGINE="duckduckgo"; npx -y open-websearch@latest
# macOS / Linux
DEFAULT_SEARCH_ENGINE=duckduckgo npx -y open-websearch@latest
# Custom port (Windows PowerShell)
$env:PORT="3100"; npx -y open-websearch@latest# Install globally
npm install -g open-websearch
# Run the server
open-websearchopen-career-ops is a local, open-source tool — NOT a hosted service. By using this software, you acknowledge:
- You control your data. Your CV, contact info, and personal data stay on your machine and are sent directly to the AI provider you choose (Anthropic, OpenAI, etc.). We do not collect, store, or have access to any of your data.
- You control the AI. The default prompts instruct the AI not to auto-submit applications, but AI models can behave unpredictably. If you modify the prompts or use different models, you do so at your own risk. Always review AI-generated content for accuracy before submitting.
- You comply with third-party ToS. You must use this tool in accordance with the Terms of Service of the career portals you interact with (Greenhouse, Lever, Workday, LinkedIn, etc.). Do not use this tool to spam employers or overwhelm ATS systems.
- No guarantees. Evaluations are recommendations, not truth. AI models may hallucinate skills or experience. The authors are not liable for employment outcomes, rejected applications, account restrictions, or any other consequences.
See LEGAL_DISCLAIMER.md for full details. This software is provided under the MIT License "as is", without warranty of any kind.
MIT
