{"id":"75543bd7-feb7-4b3b-848e-e527e2a1ec55","entityType":"agent","slug":"crewai-alyekseyenko-linkedin-jobfinder-scout","name":"linkedin-jobfinder-scout","canonicalUrl":"https://www.xpersona.co/agent/crewai-alyekseyenko-linkedin-jobfinder-scout","canonicalPath":"/agent/crewai-alyekseyenko-linkedin-jobfinder-scout","generatedAt":"2026-10-10T02:54:43.201Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T13:16:27.475Z","emptyReason":null},"description":"Operating on a Dual-Memory Neural Architecture (Candidate Memory vs. Market Memory), it integrates a Swarm of 6 Specialized AI Agents (LangGraph + CrewAI), ResumeSkills Action-Verb Technical Engine, Semantic Knowledge Graph Reasoning, pgvector Vector Database, 2-Page ATS-Optimized PDF Export, Native 1-Click LinkedIn Authentication 🧠 LinkedIn Jobfinder Scout — Autonomous Career Intelligence Engine (2026 Edition) $1 $1 $1 $1 $1 $1 $1 $1 $1 [!NOTE] **Educational & Research Notice:** This project is an open-source research and engineering showcase for multi-agent systems, human-in-the-loop browser automation, and vector memory. Always comply with the target platforms' terms of service and acceptable use guidelines. **\"Manual job hunting is obsole","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/alyekseyenko/linkedin-jobfinder-scout","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/alyekseyenko/linkedin-jobfinder-scout","kind":"source"}],"safetyScore":66,"overallRank":27,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Operating on a Dual-Memory Neural Architecture (Candidate Memory vs. Market Memory), it integrates a Swarm of 6 Specialized AI Agents (LangGraph + CrewAI), Resu"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T13:16:27.475Z","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":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T13:16:27.475Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T13:16:27.444Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T13:16:27.475Z","lastCrawledAt":"2026-10-09T13:16:27.444Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T13:16:27.444Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"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-alyekseyenko-linkedin-jobfinder-scout/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T02:54:43.201Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-alyekseyenko-linkedin-jobfinder-scout/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 REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T13:16:27.475Z","emptyReason":null},"readme":"# 🧠 LinkedIn Jobfinder Scout — Autonomous Career Intelligence Engine (2026 Edition)\n\n[![CI Quality Gate](https://github.com/alyekseyenko/linkedin-jobfinder-scout/actions/workflows/ci.yml/badge.svg)](https://github.com/alyekseyenko/linkedin-jobfinder-scout/actions)\n[![Release](https://img.shields.io/badge/Release-v2.0.0-brightgreen.svg)](https://github.com/alyekseyenko/linkedin-jobfinder-scout/releases)\n[![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-blue.svg)](https://python.org)\n[![Node.js 20+](https://img.shields.io/badge/Node.js-20%2B-green.svg)](https://nodejs.org)\n[![Docker Ready](https://img.shields.io/badge/Docker-Ready-blue.svg)](docker-compose.yml)\n[![LangGraph](https://img.shields.io/badge/AI%20Framework-LangGraph%20%2B%20CrewAI-orange)](https://github.com/langchain-ai/langgraph)\n[![PostgreSQL pgvector](https://img.shields.io/badge/Database-PostgreSQL%20%2B%20pgvector-blue)](postgres/init.sql)\n[![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![Security Policy](https://img.shields.io/badge/Security-Zero--Trust%20AES--256-blueviolet)](docs/SECURITY.md)\n\n> [!NOTE]\n> **Educational & Research Notice:** This project is an open-source research and engineering showcase for multi-agent systems, human-in-the-loop browser automation, and vector memory. Always comply with the target platforms' terms of service and acceptable use guidelines.\n\n> **\"Manual job hunting is obsolete. Welcome to Agentic Career Intelligence.\"**\n\n**LinkedIn Jobfinder Scout** is an open-source, high-performance recruitment intelligence and autonomous job application platform designed to automate, analyze, and optimize your career trajectory. \n\nOperating on a **Dual-Memory Neural Architecture (Candidate Memory vs. Market Memory)**, it integrates a **Swarm of 6 Specialized AI Agents** (LangGraph + CrewAI), **ResumeSkills Action-Verb Technical Engine**, **Semantic Knowledge Graph Reasoning**, **pgvector Vector Database**, **2-Page ATS-Optimized PDF Export**, **Native 1-Click LinkedIn Authentication**, and **Autonomous Vision-Guided Playwright Auto-Fill with Human-in-the-Loop (HITL)** to decode job postings, extract real company forensics, and complete multi-step applications safely.\n\n---\n\n## 📸 Interface Preview\n\n### 1. Job Radar & Match Scoring\n![Job Radar](docs/screenshots/dashboard.png)\n\n### 2. Application Kanban Pipeline\n![Application Pipeline](docs/screenshots/pipeline.png)\n\n### 3. Digital Twin CV & Knowledge Engine\n![Digital Twin Profile](docs/screenshots/cv_profile.png)\n\n---\n\n## 🎮 Try It Instantly — No API Keys Required\n\n```bash\ngit clone https://github.com/alyekseyenko/linkedin-jobfinder-scout.git\ncd linkedin-jobfinder-scout\ndocker compose --env-file .env.demo up\n# Open → http://localhost:5173\n```\n\nDemo mode serves pre-computed analysis results so you can explore the full UI,\nPipeline Kanban, HITL cockpit, and agent interface without any subscription.\n→ **[Full demo guide](docs/DEMO.md)**\n\n---\n\n## 🏗️ System Architecture\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│  FRONTEND  React 19 + TypeScript + Three.js           :5173     │\n└──────────────────────────┬──────────────────────────────────────┘\n                           │ REST / SSE\n┌──────────────────────────▼──────────────────────────────────────┐\n│  BACKEND   Node.js + Express                          :3004     │\n│  ┌───────────────┐ ┌──────────────┐ ┌───────────────────────┐  │\n│  │  REST Router  │ │  BullMQ      │ │  Playwright HITL      │  │\n│  │  Zod + Rate   │ │  Worker      │ │  Auto-Fill Engine     │  │\n│  │  Limiter      │ │  (isolated)  │ │  + Session Vault      │  │\n│  └───────┬───────┘ └──────┬───────┘ └───────────────────────┘  │\n└──────────┼────────────────┼─────────────────────────────────────┘\n           │                │ Redis Queue\n┌──────────▼────────────────▼─────────────────────────────────────┐\n│  AI ENGINE  Python + FastAPI + LangGraph              :8001     │\n│  ┌───────────────────────────────────────────────────────────┐  │\n│  │  3-Tier Cascading Router  (>90% token cost savings)       │  │\n│  │  Tier 1: Free heuristics  → Tier 2: Groq → Tier 3: Elite │  │\n│  └───────────────────────────┬───────────────────────────────┘  │\n│  ┌────────────────────────────▼──────────────────────────────┐  │\n│  │  6-Agent LangGraph Swarm                                  │  │\n│  │  Scout → Forensics → Evidence → Crafter → Judge          │  │\n│  └───────────────────────────────────────────────────────────┘  │\n│  ┌──────────────┐ ┌────────────────┐ ┌────────────────────┐    │\n│  │ Semantic     │ │ LLM-as-a-Judge │ │ Arize Phoenix OTLP │    │\n│  │ Cache <5ms   │ │ Hallucination  │ │ Distributed Trace  │    │\n│  └──────────────┘ └────────────────┘ └────────────────────┘    │\n└────────────────────┬────────────────────────────────────────────┘\n                     │\n┌────────────────────▼────────────────────────────────────────────┐\n│  DATA   PostgreSQL 16 + pgvector │ Redis 7 │ Qdrant (optional)  │\n└─────────────────────────────────────────────────────────────────┘\n```\n\n| Layer | Technology | Responsibility |\n|---|---|---|\n| **Presentation** | React 19 + TS + Three.js + Framer Motion | Dashboard, Pipeline, HITL Review |\n| **Orchestration** | Node.js + Express + BullMQ + Playwright | API, Queue Worker, Browser Automation |\n| **Cognitive** | Python + FastAPI + LangGraph + CrewAI | 6-Agent Swarm, Cascading Router, Judge |\n| **Persistence** | PostgreSQL + pgvector + Redis | Vector Memory, Dual-Memory, Queue |\n| **Observability** | Arize Phoenix + OTLP + Correlation IDs | Distributed Tracing, Agent Telemetry |\n\n→ **[Full architecture deep-dive](docs/ARCHITECTURE.md)** | **[Agent design decisions](docs/AGENT_DESIGN.md)**\n\n---\n\n## 🧪 Running Tests\n\n```bash\n# Python AI Engine (pytest)\ncd backend_ai && pip install -r requirements.txt\npytest test_ai_service.py test_evals_benchmark.py -v\n\n# Node.js Backend (node:test — built-in, no jest needed)\ncd backend && npm ci\nnode --test test/system.test.js test/services/*.test.js\n\n# Frontend TypeScript check + build\ncd frontend && npm ci && npm run typecheck && npm run build\n```\n\n---\n\n## ⚡ 1-Click Launch\n\n### Windows\nDouble-click the automatic launcher:\n👉 **`start-neural-scout.bat`**\n\n### Linux / macOS\n```bash\nchmod +x ./start-neural-scout.sh\n./start-neural-scout.sh\n```\n\nThe startup script automatically:\n1. Generates `.env` and `backend/user_cv.json` from templates if missing.\n2. Checks Docker daemon status.\n3. Launches all microservices (`postgres`, `ai-engine`, `neural-backend`, `neural-ui`, `qdrant`).\n4. Registers the native protocol handler for 1-Click browser authentication.\n5. Automatically opens the Dashboard in your browser at **`http://localhost:5173`**.\n\n---\n\n## 🛠️ Quickstart (Manual Setup)\n\n### 1. Clone & Setup Files\n```bash\ngit clone https://github.com/alyekseyenko/linkedin-jobfinder-scout.git\ncd linkedin-jobfinder-scout\n\n# Copy environment & profile templates\ncp .env.example .env\ncp backend/user_cv.example.json backend/user_cv.json\n```\n\n### 2. Configure Environment & Candidate CV\n- Edit `.env` with your API keys:\n  - `GROQ_API_KEY`: Ultra-fast inference for Llama 3.3 70B & DeepSeek R1 via [console.groq.com](https://console.groq.com/)\n  - `GEMINI_API_KEY`: Multimodal Vision & Reasoning via [aistudio.google.com](https://aistudio.google.com/)\n- Edit `backend/user_cv.json` with your real work history, quantifiable achievements, skills, and contact information.\n\n### 3. Start with Docker Compose\n```bash\ndocker compose up --build -d\n```\n\n---\n\n## 🔗 Microservice Ports & Web Dashboards\n\n| Service | Port / URL | Description |\n| :--- | :--- | :--- |\n| **Neural UI (Dashboard)** | [http://localhost:5173](http://localhost:5173) | Main Job Discovery, Market Intelligence & Application Cockpit |\n| **Backend API** | [http://localhost:3004](http://localhost:3004) | Orchestration Server, MCP Client & Auto-Fill Gateway |\n| **AI Engine Swagger API** | [http://localhost:8001/docs](http://localhost:8001/docs) | FastAPI Interactive Agentic Endpoint Documentation |\n| **PostgreSQL Database** | `localhost:5432` | Local PostgreSQL + pgvector Dual-Memory Database |\n| **Qdrant Vector DB** | [http://localhost:6333/dashboard](http://localhost:6333/dashboard) | High-Speed Vector Storage & Embeddings Dashboard |\n| **Arize Phoenix** | [http://localhost:6006](http://localhost:6006) | Real-time OTLP Agentic Tracing & Telemetry |\n\n---\n\n## 🔑 Native 1-Click LinkedIn Authentication & Zero-Trust Vault\n\nConnecting your LinkedIn profile no longer requires manually inspecting DevTools or copying sensitive cookies into text files:\n\n- **1-Click Native Browser Flow (`neural-login://auth`)**:\n  - Clicking **\"Connect LinkedIn\"** in the header triggers a custom native system URI handler that opens Google Chrome in your active desktop session.\n  - You log in securely on LinkedIn as usual.\n  - The system detects your active feed, automatically intercepts the session authentication token (`li_at`), and transfers it to the secure backend.\n- **Zero-Trust Encrypted Vault (`vault_service.js`)**:\n  - Session tokens and credentials are encrypted at rest using AES-256-GCM.\n  - Tokens are injected ephemerally into isolated Playwright browsing contexts without persisting plaintext credentials to shared disk images.\n- **Full Logout Lifecycle (`POST /api/auth/linkedin/logout`)**:\n  - One-click session revocation purges the Vault cache, session cookies, and environment variables instantly.\n\n---\n\n## 🤖 Live Auto-Fill Cockpit (Human-in-the-Loop — HITL)\n\nAutonomous application submission with guaranteed human oversight:\n\n```\n┌────────────────────────────────────────────────────────────────────────┐\n│  🌐 AUTONOMOUS APPLICATION PIPELINE                                    │\n│                                                                        │\n│  [Job URL] ➔ [Session Injection] ➔ [Form Detection] ➔ [pgvector RAG]   │\n│      │                                                     │           │\n│      ▼                                                     ▼           │\n│  Playwright Stealth                              Contextual Screening  │\n│  Browser Engine                                  Question Resolution   │\n│                                                            │           │\n│  🛑 HITL SAFETY GATE: Final Review Stop ────────────────────┘           │\n│      │                                                                 │\n│      ▼                                                                 │\n│  Live Screenshot Preview & Candidate Manual \"Submit\" Approval          │\n└────────────────────────────────────────────────────────────────────────┘\n```\n\n1. **Automatic Session Injection**: Directly inherits your authenticated LinkedIn session from the Vault into Playwright, bypassing login walls.\n2. **Dynamic Easy Apply Navigation**: Detects and navigates multi-step LinkedIn Easy Apply dialogs, filling candidate details (phone, email, portfolio links).\n3. **Contextual Screening Q&A**: Queries `candidate_memory` in pgvector to answer employer-specific questions (e.g., years of experience with Python/Docker, notice period, work authorization).\n4. **Human-in-the-Loop Safety Stop**:\n   - The bot automatically **halts execution at the final review screen** (`Review Application`).\n   - A real-time screenshot is streamed to the frontend dashboard.\n   - **No application is submitted without your explicit confirmation.**\n\n---\n\n## 📊 Market Intelligence & Recommended Roles Engine\n\nIntegrated directly into the header bar, the **Market Intelligence Engine** evaluates your CV against European and remote hiring trends:\n\n- **8 Strategic Roles Across 4 High-Growth Categories**:\n  - **🤖 Autonomous Agents**: *Senior Agentic AI Engineer*, *AI Systems Engineer*\n  - **⚡ Automation & Python**: *Senior Python Automation Engineer*, *Digital Transformation & AI Lead*\n  - **🧠 RAG & Knowledge Systems**: *Enterprise RAG & Knowledge Systems Engineer*, *LLM Application Developer*\n  - **🏛️ Architecture & MLOps**: *AI Infrastructure & MLOps Engineer*, *Principal AI Solutions Architect*\n- **Market Demand Signals**: Live salary benchmarking (e.g., *€70,000 - €105,000 / yr*), active job volume indicators (e.g., *350+ openings*), and match score justification.\n- **1-Click Search Binding**: Selecting any recommended role instantly loads optimized recruiter-grade search queries into the Discovery Engine without triggering accidental automated mass scraping.\n\n---\n\n## 📐 Technical Decisions (Staff/Principal Architecture)\n\n1. **pgvector vs. Cloud Vector DBs**: Chose PostgreSQL with `pgvector` for dual-memory storage (Candidate vs. Market Memory) to guarantee 100% offline data sovereignty, zero ongoing infrastructure costs, and transactional ACID consistency with relational job records.\n2. **LangGraph vs. Linear Chains**: Adopted LangGraph stateful multi-agent graphs to orchestrate cyclical feedback loops (`Scout` → `Forensics` → `Crafter` → `Recruiter Mirror` self-correction) rather than naive sequential pipelines.\n3. **BullMQ / Redis vs. Polling Interval**: Migrated background AI analysis and high-latency web scrapers into an isolated BullMQ worker process with concurrency control, retry backoff with jitter, and rate-limit quarantine.\n4. **Cascading 3-Tier Inference**: Implemented an automated confidence cascade routing jobs to fast/free models for initial triage (<60% match) and reserving heavy multimodal models only for elite opportunities (>=80%), slashing API billing by >90%.\n5. **Zero-Trust Session Vault (AES-256-GCM)**: Authenticated cookies and tokens are encrypted at rest with PBKDF2 key derivation and injected ephemerally into Playwright browsing contexts without ever writing plaintext credentials to shared Docker volumes.\n\n---\n\n## ❓ Useful Commands\n\n```bash\n# View live container logs\ndocker compose logs -f\n\n# Check backend logs specifically\ndocker compose logs -f neural-backend\n\n# Stop all microservices\ndocker compose down\n\n# Rebuild containers from scratch\ndocker compose up --build -d\n```\n\n---\n\n## 🛡️ Privacy & Security\n\n- **100% Local Execution**: All CV data (`user_cv.json`), vector memories, and database records remain strictly on your local machine.\n- **Zero-Trust Token Storage**: LinkedIn session cookies are stored in an AES-256 encrypted vault, never committed to git or exposed in plaintext logs.\n- **Safety-First Automation**: The system is designed strictly as a Human-in-the-Loop co-pilot; it never submits applications or dispatches outreach messages without explicit human approval.\n\n---\n\n## 📄 License\n\nDistributed under the **MIT License**. Free for personal and open-source use.\n","readmeExcerpt":"🧠 LinkedIn Jobfinder Scout — Autonomous Career Intelligence Engine (2026 Edition) $1 $1 $1 $1 $1 $1 $1 $1 $1 [!NOTE] **Educational & Research Notice:** This project is an open-source research and engineering showcase for multi-agent systems, human-in-the-loop browser automation, and vector memory. Always comply with the target platforms' terms of service and acceptable use guidelines. **\"Manual job hunting is obsole","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"git clone https://github.com/alyekseyenko/linkedin-jobfinder-scout.git\ncd linkedin-jobfinder-scout\ndocker compose --env-file .env.demo up\n# Open → http://localhost:5173"},{"language":"text","snippet":"┌─────────────────────────────────────────────────────────────────┐\n│  FRONTEND  React 19 + TypeScript + Three.js           :5173     │\n└──────────────────────────┬──────────────────────────────────────┘\n                           │ REST / SSE\n┌──────────────────────────▼──────────────────────────────────────┐\n│  BACKEND   Node.js + Express                          :3004     │\n│  ┌───────────────┐ ┌──────────────┐ ┌───────────────────────┐  │\n│  │  REST Router  │ │  BullMQ      │ │  Playwright HITL      │  │\n│  │  Zod + Rate   │ │  Worker      │ │  Auto-Fill Engine     │  │\n│  │  Limiter      │ │  (isolated)  │ │  + Session Vault      │  │\n│  └───────┬───────┘ └──────┬───────┘ └───────────────────────┘  │\n└──────────┼────────────────┼─────────────────────────────────────┘\n           │                │ Redis Queue\n┌──────────▼────────────────▼─────────────────────────────────────┐\n│  AI ENGINE  Python + FastAPI + LangGraph              :8001     │\n│  ┌───────────────────────────────────────────────────────────┐  │\n│  │  3-Tier Cascading Router  (>90% token cost savings)       │  │\n│  │  Tier 1: Free heuristics  → Tier 2: Groq → Tier 3: Elite │  │\n│  └───────────────────────────┬───────────────────────────────┘  │\n│  ┌────────────────────────────▼──────────────────────────────┐  │\n│  │  6-Agent LangGraph Swarm                                  │  │\n│  │  Scout → Forensics → Evidence → Crafter → Judge          │  │\n│  └───────────────────────────────────────────────────────────┘  │\n│  ┌──────────────┐ ┌────────────────┐ ┌────────────────────┐    │\n│  │ Semantic     │ │ LLM-as-a-Judge │ │ Arize Phoenix OTLP │    │\n│  │ Cache <5ms   │ │ Hallucination  │ │ Distributed Trace  │    │\n│  └──────────────┘ └────────────────┘ └────────────────────┘    │\n└────────────────────┬────────────────────────────────────────────┘\n                     │\n┌────────────────────▼────────────────────────────────────────────┐\n│  DATA   PostgreSQL 16 + pgvector │ Redis 7 │ Qdrant (optional)  │\n└─"},{"language":"bash","snippet":"# Python AI Engine (pytest)\ncd backend_ai && pip install -r requirements.txt\npytest test_ai_service.py test_evals_benchmark.py -v\n\n# Node.js Backend (node:test — built-in, no jest needed)\ncd backend && npm ci\nnode --test test/system.test.js test/services/*.test.js\n\n# Frontend TypeScript check + build\ncd frontend && npm ci && npm run typecheck && npm run build"},{"language":"bash","snippet":"chmod +x ./start-neural-scout.sh\n./start-neural-scout.sh"},{"language":"bash","snippet":"git clone https://github.com/alyekseyenko/linkedin-jobfinder-scout.git\ncd linkedin-jobfinder-scout\n\n# Copy environment & profile templates\ncp .env.example .env\ncp backend/user_cv.example.json backend/user_cv.json"},{"language":"bash","snippet":"docker compose up --build -d"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"Operating on a Dual-Memory Neural Architecture (Candidate Memory vs. Market Memory), it integrates a Swarm of 6 Specialized AI Agents (LangGraph + CrewAI), ResumeSkills Action-Verb Technical Engine, Semantic Knowledge Graph Reasoning, pgvector Vector Database, 2-Page ATS-Optimized PDF Export, Native 1-Click LinkedIn Authentication 🧠 LinkedIn Jobfinder Scout — Autonomous Career Intelligence Engine (2026 Edition) $1 $1 $1 $1 $1 $1 $1 $1 $1 [!NOTE] **Educational & Research Notice:** This project is an open-source research and engineering showcase for multi-agent systems, human-in-the-loop browser automation, and vector memory. Always comply with the target platforms' terms of service and acceptable use guidelines. **\"Manual job hunting is obsole","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":409,"uniquenessScore":70,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T13:16:27.475Z","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":"2026-10-09T13:16:27.475Z","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":"2026-10-10T02:54:43.201Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}