{"adoption": {"forks": 576, "observed_at": "2026-08-28T04:10:28.944780+00:00", "stars": 9222}, "canonical_url": "https://ross.abutalabs.com/products/xberg", "card": {"archived": false, "artifact_type": "framework", "description": "A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API, and MCP server.", "domain": ["artificial-intelligence", "pdf", "files", "developer-tools"], "enriched": true, "function": ["parser", "ocr", "pdf", "rag", "nlp", "machine-learning", "web-scraping", "cli", "sdk", "mcp", "data-generation"], "health_score": 100, "homepage": "https://docs.xberg.io", "language": "Rust", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["xberg-io/xberg"], "name": "xberg-io/xberg", "platform": ["rust", "python", "go", "jvm", "dotnet", "ruby", "php", "elixir", "wasm", "cli", "cross-platform", "windows"], "pushed_at": "2026-08-26T11:06:09+00:00", "repo": "xberg-io/xberg", "stars": 9222, "tags": ["document-intelligence", "text-extraction", "pdf-to-markdown", "table-extraction", "whisper-transcription", "ffi-bindings", "rest-api", "code-intelligence", "embeddings", "entity-extraction", "natural-language-processing", "retrieval-augmented-generation", "data-engineering", "nodejs", "docker", "linux", "macos"], "topics": ["text-extraction", "document-intelligence", "metadata-extraction", "pdf-extraction", "pdfium", "python", "rag", "table-extraction", "tesseract", "ffi", "golang", "java", "node", "ruby", "rust", "wasm", "elixir", "php", "bun", "csharp"], "urls": [], "use_cases": ["extract text and tables from pdfs to markdown", "parse resumes and office documents into structured data", "ocr scanned documents into searchable text", "transcribe audio and video files with whisper", "build a rag pipeline over documents with embeddings", "extract entities and json matching a schema from documents", "crawl a url and extract page content", "parse functions and imports from source code files"], "what_it_is": "Xberg is a polyglot document intelligence framework with a Rust core that extracts text, metadata, tables, images, and structured data from 100+ file formats, plus code intelligence for 371 languages. It ships 15 language bindings, a CLI, a REST API, and an MCP server, with OCR, audio transcription, web crawling, and LLM-based structured extraction built in.", "when_to_avoid": ["you only need simple pdf text extraction and a lightweight tool suffices", "your CPU lacks AVX/AVX2 and you need ONNX-dependent features like PaddleOCR or embeddings", "you need HEIC/AVIF decoding on wasm or android targets", "you require a pure-permissive license build since libheif is LGPL"], "when_to_choose": ["you need one engine for many document formats instead of stitching libraries together", "you want native-speed extraction with bindings for your language of choice", "you need OCR, transcription, crawling, and structured extraction in a single API", "you want an MCP server or REST API for document extraction"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/xberg", "repo": "xberg-io/xberg", "role": "main", "score": 86}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.944780+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:23:16.802983+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db3f274d6a09b1f23d39afd6ffbd0a2b15bbfb9482f21c2c9ac3216c82cfc1a9", "fetched_at": "2026-08-28T04:10:28.944780+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xberg-io/xberg"}, {"content_hash": "4d806a46bd59a62679b8bf5966116fd5b20b3ea5b75f4b2aa906275fc5eef250", "fetched_at": "2026-08-29T08:23:10.071348+00:00", "kind": "homepage", "missing": false, "url": "https://docs.xberg.io"}, {"content_hash": "94c976b8b01e7d3c3d75981dd78b77325da39157bcd8940d164b732ed78a1a1b", "fetched_at": "2026-08-29T08:23:10.080489+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/quickstart"}, {"content_hash": "065d1fc5763ca52939532a284d2f7704a2eea29649767daaf9318056835fb7e6", "fetched_at": "2026-08-29T08:23:10.083468+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/getting-started/installation"}, {"content_hash": "9854ab2097cc84a09711634aa0a1fb1a0fbb3d1b3624a2858ea5d287c4f4489b", "fetched_at": "2026-08-29T08:23:10.085872+00:00", "kind": "site_page", "missing": false, "url": "https://docs.xberg.io/features"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 41, "rhythm": 96}, "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": 579, "days_push": 7, "days_rel": 29, "gap_med": 0.0, "n_releases_24m": 31}, "score": 86, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}