{"repo":"cortex-works/cortex-scout","free":true,"listed":false,"github":"https://github.com/cortex-works/cortex-scout","clone":"git clone https://github.com/cortex-works/cortex-scout.git","description":"A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.","language":"Rust","stars":69,"topics":["ai-agents","rust","searxng","self-hosted","semantic-search","web-scraping","anti-bot-bypass","dev-tools","knowledge-graph","llm-tools"],"license":"MIT","category":"scrapers-browser-automation","readme_excerpt":"CortexScout (cortex-scout) — Search and Web Extraction Engine for AI Agents CortexScout is the Deep Research & Web Extraction module within the Cortex-Works ecosystem. Designed for agent workloads that require token-efficient web retrieval, reliable anti-bot handling, and optional Human-in-the-Loop (HITL) fallback. --- Overview CortexScout provides a single, self-hostable Rust binary that exposes search, extraction, and stateful browser automation capabilities over MCP (stdio) and an optional HTTP server. Output formats are structured and optimized for downstream LLM use. It is built to handle the practical failure modes of web retrieval (rate limits, bot challenges, JavaScript-heavy pages) through progressive fallbacks: native retrieval → Chromium CDP rendering → Stateful E2E Testing → HITL workflows. --- Tools (Capability Roster) Area MCP Tools / Capabilities ------ --------------------------- Search web search (URL discovery) or web search(include content=true) (search+content in one call) Fetch and Crawl web fetch(mode=\"single\" \"batch\" \"crawl\") (unified fetch family) Extraction extract fields (primary structured extraction) Automation scout browser automate / browser automate (stateful omni-tool), scout agent profile auth , scout browser close Anti-bot handling CDP rendering, proxy rotation, block-aware retries HITL visual scout , hitl web fetch(auth mode=\"challenge\" \"auth\") Memory memory search (LanceDB-backed research history) Deep research deep research (multi-hop sear","default_branch":null,"files":null,"tree":[],"storefront":"/r/cortex-works","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/cortex-works/cortex-scout/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}