{"adoption": {"forks": 178, "observed_at": "2026-08-28T04:08:34.412290+00:00", "stars": 4082}, "canonical_url": "https://ross.abutalabs.com/products/airobotstxt", "card": {"archived": false, "artifact_type": "dataset", "description": "A list of AI agents and robots to block.", "domain": ["privacy", "web-development", "crawlers", "self-hosted"], "enriched": true, "function": ["security", "web-scraping", "configuration-management"], "health_score": 100, "homepage": "https://github.com/ai-robots-txt/ai.robots.txt/releases.atom", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["ai-robots-txt/ai.robots.txt"], "name": "ai-robots-txt/ai.robots.txt", "platform": ["self-hosted", "cli"], "pushed_at": "2026-08-26T22:55:38+00:00", "repo": "ai-robots-txt/ai.robots.txt", "stars": 4082, "tags": ["robots-txt", "ai-crawlers", "bot-blocking", "nginx", "apache", "caddy", "haproxy", "lighttpd", "user-agent-filtering", "web-server"], "topics": ["ai", "crawlers", "crawling", "privacy"], "urls": [], "use_cases": ["block AI crawlers from my website", "generate a robots.txt that disallows AI bots", "block GPTBot and ClaudeBot in nginx", "stop AI companies from scraping my content for training", "configure HAProxy to deny AI user agents", "find a list of AI scraper user agents"], "what_it_is": "A community-maintained list of AI crawler user agents, distributed as robots.txt plus ready-made blocking configs for Apache, Nginx, Caddy, HAProxy, and lighttpd. It lets website owners block AI training and scraping bots from their sites.", "when_to_avoid": ["you need to block bots that ignore robots.txt and spoof user agents - use behavioral detection or a WAF instead", "you run a CDN or managed platform where you cannot edit server configs", "you want to allow some AI crawlers but block others with fine-grained policy"], "when_to_choose": ["you self-host a website and want to block AI crawlers at the server or robots.txt level", "you want a regularly updated, community-maintained list of AI bot user agents", "you need drop-in config snippets for common web servers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/airobotstxt", "repo": "ai-robots-txt/ai.robots.txt", "role": "main", "score": 92}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:34.412290+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:23:25.032433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a841826b8f861f8886c4d945e92307a0ead48da16bb8e640d103b8e23212256", "fetched_at": "2026-08-28T04:08:34.412290+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ai-robots-txt/ai.robots.txt"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 63, "rhythm": 99}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 889, "days_push": 7, "days_rel": 7, "gap_med": 13, "n_releases_24m": 36}, "score": 92, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}