{"slug": "openingress-agent-crawl-and-navigation-checks", "title": "OpenIngress – agent crawl and navigation checks", "summary": "OpenIngress, an open-source tool that audits whether autonomous agents can complete real buyer flows on e-commerce sites, launched on GitHub. It crawls rendered pages, runs static operability checks, and simulates agent-style navigation to produce readiness scores and fix prompts. The project addresses the gap between AI visibility (AEO/GEO) and actual agent operability.", "body_md": "**Audits whether autonomous agents can complete real buyer flows.**\n\nRendered crawl, operability checks, simulated navigation, evidence reports.\n\n[openingress.dev](https://openingress.dev) ·\n[LinkedIn](https://www.linkedin.com/company/openingress) ·\n[Features](#what-you-get)\n\nOpenIngress crawls rendered pages, runs static operability checks, simulates agent-style navigation, and produces evidence-heavy reports with fix prompts and remediation exports.\n\nThis repository includes the open-source backend and an optional Vue frontend. The backend is the main artifact. The hosted site at [openingress.dev](https://www.openingress.dev) offers a demo report and contact flow.\n\n**AEO** and **GEO** help AI systems *find* and *cite* your store. That does not mean an agent can *shop* it.\n\n| Layer | What it solves |\n|---|---|\nAEO / GEO |\nBrand visibility in AI answers — \"this store sells workout gear\" |\nIntra-site navigation |\nMachine-readable commerce on the live site — sizes in stock, cart state, checkout handoff |\n\nOpenIngress audits the second layer: whether an agent can traverse catalog → product → cart → checkout, not whether your marketing pages rank in an answer box. More detail in [docs/ARCHITECTURE.md](/Open-Ingress/OpenIngress/blob/main/docs/ARCHITECTURE.md).\n\n**Rendered crawl**— screenshots, HTML, and accessibility trees** Static operability**— label coverage, DOM health,`llms.txt`\n\n, hydration gaps**Agent exploration**— heuristic or LLM-guided navigation through discovery → product → cart → checkout** Buyer-flow evidence**— funnel steps with pass/fail, blockers, and screenshot replay** Readiness score**— headline metric plus revenue-ranked blockers** Fix packs**— implementation prompts and Markdown/PDF exports** Dashboard**— Vue app for audits, runs, reports, and fixes\n\nSample report: [openingress.dev](https://openingress.dev) or `/reports/demo`\n\nlocally (no backend required).\n\n**Requirements:** Python 3.10+, Node.js 18+, Chromium (via Playwright)\n\n```\ngit clone https://github.com/Open-Ingress/OpenIngress.git\ncd OpenIngress\n\ncp .env.example .env\ncp backend/.env.example backend/.env\ncp frontend/.env.example frontend/.env\n\nmake install\nmake backend   # terminal 1 → http://127.0.0.1:5055\nmake frontend  # terminal 2 → http://localhost:5175\n```\n\nOpen ** http://localhost:5175** →\n\n**New audit**→ enter a storefront URL.\n\nBrowser automation uses **Playwright** for the crawl layer. Exploration and scoring sit on top: accessibility-tree inspection, navigation-graph analysis, operability checks, and report generation.\n\n``` php\nflowchart LR\n  URL[Storefront URL] --> Crawl[Rendered crawl]\n  Crawl --> Static[Static checks]\n  Crawl --> Explore[Agent exploration]\n  Static --> Report[Readiness report]\n  Explore --> Report\n  Report --> Fixes[Fix prompts + exports]\n```\n\n**Crawl**— discover pages, capture HTML, screenshots, and aria snapshots** Analyze**— score operability, map navigation, detect commerce funnel steps** Explore**— agent-style clicks through the buyer journey** Report**— scores, blockers, traces, and remediation exports\n\n| Path | Purpose |\n|---|---|\n`backend/` |\n\n`frontend/`\n\n`docs/`\n\n`frontend/public/demo-report/`\n\n`/reports/demo`\n\n`Dockerfile`\n\n| Guide | Description |\n|---|---|\n|\n\n[API reference](/Open-Ingress/OpenIngress/blob/main/docs/API.md)[Deployment](/Open-Ingress/OpenIngress/blob/main/docs/SELF_HOST.md)[Development](/Open-Ingress/OpenIngress/blob/main/docs/DEVELOPMENT.md)| Variable | Where | Purpose |\n|---|---|---|\n`LLM_API_KEY` |\n`backend/.env` |\nOpenAI-compatible key for agent exploration |\n`LLM_BASE_URL` |\n`backend/.env` |\nAny compatible endpoint (Ollama, Azure, etc.) |\n`VITE_API_URL` |\n`frontend/.env` |\nBackend API base (`http://127.0.0.1:5055/api/ingress` ) |\n\nFull reference: [docs/SELF_HOST.md](/Open-Ingress/OpenIngress/blob/main/docs/SELF_HOST.md)\n\n```\nmake test\nmake smoke   # backend must be running\n```\n\nSee [CONTRIBUTING.md](/Open-Ingress/OpenIngress/blob/main/CONTRIBUTING.md) and [docs/DEVELOPMENT.md](/Open-Ingress/OpenIngress/blob/main/docs/DEVELOPMENT.md).", "url": "https://wpnews.pro/news/openingress-agent-crawl-and-navigation-checks", "canonical_source": "https://github.com/Open-Ingress/OpenIngress", "published_at": "2026-07-11 19:01:07+00:00", "updated_at": "2026-07-11 19:35:26.321910+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "ai-infrastructure", "autonomous-vehicles"], "entities": ["OpenIngress", "Playwright", "GitHub", "Vue", "OpenAI", "Ollama", "Azure"], "alternates": {"html": "https://wpnews.pro/news/openingress-agent-crawl-and-navigation-checks", "markdown": "https://wpnews.pro/news/openingress-agent-crawl-and-navigation-checks.md", "text": "https://wpnews.pro/news/openingress-agent-crawl-and-navigation-checks.txt", "jsonld": "https://wpnews.pro/news/openingress-agent-crawl-and-navigation-checks.jsonld"}}