{"id":"549d4831-fbf7-4ca1-888c-383bf77a63ff","entityType":"agent","slug":"crewai-sakshi3027-contractor-intelligence","name":"contractor-intelligence","canonicalUrl":"https://www.xpersona.co/agent/crewai-sakshi3027-contractor-intelligence","canonicalPath":"/agent/crewai-sakshi3027-contractor-intelligence","generatedAt":"2026-10-09T00:08:57.774Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-05-31T06:18:14.015Z","emptyReason":null},"description":"Agentic lead intelligence system discovers IT contractor partners, scores them with self-improving XGBoost + SHAP, generates personalized outreach via CrewAI agents, orchestrated with Temporal workflows Contractor Intelligence An agentic lead intelligence system that autonomously discovers IT service contractor partners, scores them with a self-improving ML model, and generates personalized outreach via LLM agents — with a full data pipeline tracking conversion outcomes. **🔗 Live Demo: $1** --- Screenshots 1. Main Dashboard The main dashboard gives you a real-time overview of the entire system. The five stat cards","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 5/31/2026.","installCommand":"git clone https://github.com/Sakshi3027/contractor-intelligence.git","sourceUrl":"https://github.com/Sakshi3027/contractor-intelligence","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/Sakshi3027/contractor-intelligence","kind":"source"}],"safetyScore":66,"overallRank":32.8,"popularityScore":8,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Agentic lead intelligence system discovers IT contractor partners, scores them with self-improving XGBoost + SHAP, generates personalized outreach via CrewAI ag"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-05-31T06:18:14.015Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"medium","updatedAt":"2026-05-31T06:18:14.015Z","emptyReason":null},"stars":1,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":"1 GitHub stars"},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-05-31T06:18:14.014Z","emptyReason":null},"lastUpdatedAt":"2026-05-31T06:18:14.015Z","lastCrawledAt":"2026-05-31T06:18:14.014Z","lastIndexedAt":null,"nextCrawlAt":"2026-06-07T06:18:14.014Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/Sakshi3027/contractor-intelligence.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T00:08:57.774Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-contractor-intelligence/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-05-31T06:18:14.015Z","emptyReason":null},"readme":"# Contractor Intelligence\n\n> An agentic lead intelligence system that autonomously discovers IT service contractor partners, scores them with a self-improving ML model, and generates personalized outreach via LLM agents — with a full data pipeline tracking conversion outcomes.\n\n![Dashboard](https://img.shields.io/badge/Dashboard-Next.js-black?style=flat-square&logo=next.js)\n![API](https://img.shields.io/badge/API-FastAPI-009688?style=flat-square&logo=fastapi)\n![ML](https://img.shields.io/badge/ML-XGBoost%20%2B%20SHAP-orange?style=flat-square)\n![Agents](https://img.shields.io/badge/Agents-CrewAI%20%2B%20Groq-purple?style=flat-square)\n![Pipeline](https://img.shields.io/badge/Pipeline-Temporal-blue?style=flat-square)\n![Live](https://img.shields.io/badge/Live-Vercel-black?style=flat-square&logo=vercel)\n\n**🔗 Live Demo: [contractor-intel-five.vercel.app](https://contractor-intel-five.vercel.app)**\n\n---\n\n## Screenshots\n\n### 1. Main Dashboard\n![Dashboard](https://raw.githubusercontent.com/Sakshi3027/contractor-intelligence/main/assets/dashboard.png)\n\nThe main dashboard gives you a real-time overview of the entire system. The five stat cards show total businesses discovered (17), hot leads identified by the ML model (7), warm leads, average lead score across all businesses (0.408), and outreach emails sent. The bar chart below breaks down lead distribution by city red bars are hot leads, blue are cold so you can instantly see which markets have the most opportunity. Boston, Chicago, and New York are the three target cities in this run.\n\n---\n\n### 2. Lead Scoring Table\n![Leads Table](https://raw.githubusercontent.com/Sakshi3027/contractor-intelligence/main/assets/leads-table.png)\n\nEvery discovered business gets scored by the XGBoost model using 24 engineered features Google rating, review count, website quality, contact completeness, and more. The score bar visually shows relative quality, and each lead is classified as 🔥 hot (score ≥ 0.70), 🌤 warm (0.40–0.70), or ❄️ cold (below 0.40). Hot leads like Micro-Tech USA, Boston IT, and Power Consulting Group score 0.738 and are immediately queued for AI agent outreach. The table is sortable and filterable by tier and city.\n\n---\n\n### 3. Lead Distribution by City\n![Chart](https://raw.githubusercontent.com/Sakshi3027/contractor-intelligence/main/assets/chart.png)\n\nThe interactive bar chart shows how leads are distributed across cities and tiers. Hovering over a city (Boston shown here) reveals the exact breakdown 3 hot leads and 4 cold leads in Boston. This view helps identify which cities are producing the highest quality leads so the pipeline can be prioritized accordingly. Chicago has the most hot leads in this run, making it the top target market for outreach.\n\n---\n\n## What Makes This Different\n\nMost lead generation tools are static scripts. This system:\n\n- **Learns over time** — XGBoost model retrains automatically as outcome data accumulates\n- **Multi-agent research** — CrewAI agents research each business before writing personalized outreach\n- **Full data flywheel** — Discovery → Scoring → Outreach → Outcomes → Retraining, all automated\n- **5 database paradigms** — PostgreSQL, MongoDB, ClickHouse, Qdrant, Redis in one system\n- **Production-grade infra** — Temporal workflows, Prometheus monitoring, 11 Docker containers\n\n---\n\n## Tech Stack\n\n### AI / ML\n| Tool | Purpose |\n|------|---------|\n| XGBoost + SHAP | Lead scoring with explainability |\n| MLflow | Experiment tracking + model versioning |\n| CrewAI | Multi-agent orchestration |\n| Groq (llama-3.3-70b) | Ultra-fast LLM inference |\n\n### Data Engineering\n| Tool | Purpose |\n|------|---------|\n| Temporal | Workflow orchestration |\n| Apache Flink | Real-time scoring stream |\n| dbt | Data transformation layer |\n\n### Databases\n| Database | Type | Purpose |\n|----------|------|---------|\n| PostgreSQL | Relational | Scores, outreach, outcomes |\n| MongoDB | Document | Raw profiles, agent research |\n| ClickHouse | Columnar | Analytics + funnel metrics |\n| Qdrant | Vector | Semantic lead matching |\n| Redis | Cache | Job queues + caching |\n\n### Backend + Frontend\n| Tool | Purpose |\n|------|---------|\n| FastAPI | REST API (12 endpoints) |\n| Strawberry | GraphQL layer |\n| Next.js | Dashboard UI |\n| Recharts | Data visualization |\n\n### DevOps\n| Tool | Purpose |\n|------|---------|\n| Docker Compose | 11 containers |\n| Prometheus + Grafana | Monitoring |\n| GitHub Actions | CI/CD |\n| Terraform | GCP IaC |\n\n---\n\n## Quick Start\n\n### Prerequisites\n- Docker + Docker Compose\n- Python 3.12+\n- Node.js 18+\n- API keys: Google Places, Groq, Hunter.io\n\n### 1. Clone and setup\n    git clone https://github.com/Sakshi3027/contractor-intelligence.git\n    cd contractor-intelligence\n    cp .env.example .env\n    # Fill in your API keys in .env\n\n### 2. Start all services\n    docker-compose up -d\n\n### 3. Initialize databases\n    docker exec -i contractor_postgres psql -U contractor_user -d contractor_db < infrastructure/docker/init_postgres.sql\n    docker exec -i contractor_mongodb mongosh < infrastructure/docker/init_mongodb.js\n    docker exec -i contractor_clickhouse clickhouse-client --multiquery < infrastructure/docker/init_clickhouse.sql\n\n### 4. Install Python dependencies\n    cd services\n    python -m venv venv\n    source venv/bin/activate\n    pip install -r requirements.txt\n\n### 5. Run the pipeline\n    # Terminal 1 — Start Temporal worker\n    python -m pipeline.temporal.worker\n\n    # Terminal 2 — Trigger pipeline\n    python -m pipeline.temporal.scheduler\n\n### 6. Start the API\n    python -m uvicorn api.main:app --host 0.0.0.0 --port 8001 --reload\n\n### 7. Start the dashboard\n    cd ../frontend\n    npm install\n    npm run dev\n    # Open https://contractor-intel-five.vercel.app\n\n---\n\n## Pipeline Phases\n\n**Phase 1: Discovery**\n- Google Places API — 15+ IT businesses per city\n- Playwright scraper — website content\n- Hunter.io — email discovery (87% success rate)\n\n**Phase 2: ML Scoring**\n- 24 engineered features per business\n- XGBoost classifier with cross-validation\n- SHAP explainability per lead\n- MLflow experiment tracking\n\n**Phase 3: AI Agents**\n- Research Agent — analyzes each business profile\n- Email Agent — writes personalized outreach\n- CrewAI orchestration with Groq inference\n\n**Phase 4: Pipeline Automation**\n- Temporal workflows — full orchestration\n- Auto-retry on failure\n- Scheduled runs across cities\n\n**Phase 5: Feedback Loop**\n- Track outreach outcomes (opened, replied, converted)\n- Auto-retrain model when 10+ outcomes collected\n- Model improves over time — real data flywheel\n\n---\n\n## Services\n\n| Service | URL | Description |\n|---------|-----|-------------|\n| Dashboard | https://contractor-intel-five.vercel.app | Next.js UI |\n| API Docs | http://34.23.97.178:8001/docs | FastAPI Swagger |\n| MLflow | http://34.23.97.178:5002 | Experiment tracking |\n| Temporal UI | http://34.23.97.178:8888 | Workflow monitoring |\n| Grafana | http://34.23.97.178:3001 | System monitoring |\n| Prometheus | http://34.23.97.178:9090 | Metrics |\n| Qdrant | http://34.23.97.178:6333/dashboard | Vector DB UI |\n\n---\n\n## Project Structure\n\n    contractor-intelligence/\n    services/\n        discovery/          # Google Places + email finder\n        scoring/            # XGBoost + SHAP + MLflow\n        agents/             # CrewAI research + email agents\n        api/                # FastAPI REST + GraphQL\n        pipeline/\n            temporal/       # Workflows + activities + worker\n    frontend/               # Next.js dashboard\n    infrastructure/\n        docker/             # DB init scripts\n        terraform/          # GCP IaC\n    monitoring/             # Prometheus config\n    data/\n        models/             # Trained model artifacts\n    docker-compose.yml      # 11 services\n\n---\n\n## The Self-Improving Loop\n\nNew businesses are discovered → ML model scores them → AI agents research and write personalized emails → outreach is sent and tracked → outcomes are recorded → model retrains on new data → better scores next time.\n\nThis feedback loop is what separates this from a simple scraper. The system gets smarter with every outreach cycle.\n\n---\n\n## Author\n\n**Sakshi Chavan** — Software Engineer | Data Scientist | ML Engineer | New York, USA\n\nGitHub: https://github.com/Sakshi3027\n","readmeExcerpt":"Contractor Intelligence An agentic lead intelligence system that autonomously discovers IT service contractor partners, scores them with a self-improving ML model, and generates personalized outreach via LLM agents — with a full data pipeline tracking conversion outcomes. **🔗 Live Demo: $1** --- Screenshots 1. Main Dashboard The main dashboard gives you a real-time overview of the entire system. The five stat cards ","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Agentic lead intelligence system discovers IT contractor partners, scores them with self-improving XGBoost + SHAP, generates personalized outreach via CrewAI agents, orchestrated with Temporal workflows Contractor Intelligence An agentic lead intelligence system that autonomously discovers IT service contractor partners, scores them with a self-improving ML model, and generates personalized outreach via LLM agents — with a full data pipeline tracking conversion outcomes. **🔗 Live Demo: $1** --- Screenshots 1. Main Dashboard The main dashboard gives you a real-time overview of the entire system. The five stat cards","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":384,"uniquenessScore":67,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-05-31T06:18:14.015Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-05-31T06:18:14.015Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T00:08:57.774Z","emptyReason":null},"items":[{"id":"959108e7-5f7c-45ac-bea0-9ab67f017226","entityType":"agent","canonicalPath":"/agent/langchain-x1pay-langchain","slug":"langchain-x1pay-langchain","name":"@x1pay/langchain","description":"LangChain/LangGraph tools for AI agent x402 payments on X1","url":"https://www.npmjs.com/package/@x1pay/langchain","homepage":null,"source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:07.099Z","createdAt":"2026-05-23T06:52:58.553Z","downloads":null},{"id":"4f8f8f95-34f7-49a9-b516-391d1c355d6c","entityType":"agent","canonicalPath":"/agent/langchain-langchain-langgraph-swarm","slug":"langchain-langchain-langgraph-swarm","name":"@langchain/langgraph-swarm","description":"An implementation of a multi-agent swarm using LangGraph","url":"git+ssh://git@github.com/langchain-ai/langgraphjs.git","homepage":"https://github.com/langchain-ai/langgraphjs#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:03.792Z","createdAt":"2026-05-23T06:52:55.396Z","downloads":null},{"id":"e36fd59b-38d7-4e73-aa20-c1431a8f7434","entityType":"agent","canonicalPath":"/agent/langchain-langchain-langgraph-supervisor","slug":"langchain-langchain-langgraph-supervisor","name":"@langchain/langgraph-supervisor","description":"LangGraph Multi-Agent Supervisor","url":"git+ssh://git@github.com/langchain-ai/langgraphjs.git","homepage":"https://github.com/langchain-ai/langgraphjs#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:03.756Z","createdAt":"2026-05-23T06:52:55.353Z","downloads":null},{"id":"d1d0f93e-b722-4791-9bbf-2532470054c2","entityType":"agent","canonicalPath":"/agent/langchain-oceanbus-langchain","slug":"langchain-oceanbus-langchain","name":"oceanbus-langchain","description":"LangChain tools for OceanBus — give your LangChain and CrewAI agents a global identity, encrypted messaging, and Yellow Pages service discovery with a single import.","url":"git+https://github.com/oceanbus/oceanbus.git","homepage":"https://github.com/oceanbus/oceanbus#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":["oceanbus","langchain","langchain-tools","agent-to-agent","ai-agent","communication","messaging","e2ee","structured-tool","yellow-pages","service-discovery","reputation","crewai"],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:02.595Z","createdAt":"2026-05-23T06:52:54.240Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}