{
  "feed": "RAG Repo - recently added and reviewed sources",
  "site": "https://rag-repo.org",
  "generated": "2026-09-16",
  "note": "Ordered by lastReviewed (YYYY-MM-DD), newest first. Poll to detect new or re-reviewed sources; the full catalogue is at /sources.json.",
  "count": 60,
  "items": [
    {
      "slug": "case-network",
      "name": "CASE Network (1EdTech)",
      "page": "https://rag-repo.org/source/case-network",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "ck-12",
      "name": "CK-12 Foundation",
      "page": "https://rag-repo.org/source/ck-12",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "common-core",
      "name": "Common Core State Standards",
      "page": "https://rag-repo.org/source/common-core",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "khan-academy",
      "name": "Khan Academy",
      "page": "https://rag-repo.org/source/khan-academy",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "unknown",
      "supersedes": []
    },
    {
      "slug": "ngss",
      "name": "Next Generation Science Standards",
      "page": "https://rag-repo.org/source/ngss",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "saylor-academy",
      "name": "Saylor Academy",
      "page": "https://rag-repo.org/source/saylor-academy",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "siyavula",
      "name": "Siyavula",
      "page": "https://rag-repo.org/source/siyavula",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "uk-national-curriculum",
      "name": "UK National Curriculum (England)",
      "page": "https://rag-repo.org/source/uk-national-curriculum",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "wikiversity",
      "name": "Wikiversity",
      "page": "https://rag-repo.org/source/wikiversity",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-15",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "alphafold-protein-structure-database",
      "name": "AlphaFold Protein Structure Database",
      "page": "https://rag-repo.org/source/alphafold-protein-structure-database",
      "category": "biomedical",
      "categoryName": "Biomedical & health",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "bfcl",
      "name": "Berkeley Function-Calling Leaderboard (BFCL)",
      "page": "https://rag-repo.org/source/bfcl",
      "category": "agentic-tool-use",
      "categoryName": "Agentic & Tool-Use",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "bigpatent",
      "name": "BIGPATENT",
      "page": "https://rag-repo.org/source/bigpatent",
      "category": "patents",
      "categoryName": "Patents & intellectual property",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "essential-web",
      "name": "Essential-Web v1.0",
      "page": "https://rag-repo.org/source/essential-web",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": "v1.0",
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "huge",
      "supersedes": []
    },
    {
      "slug": "finepdfs",
      "name": "FinePDFs",
      "page": "https://rag-repo.org/source/finepdfs",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "fineweb-edu",
      "name": "FineWeb-Edu",
      "page": "https://rag-repo.org/source/fineweb-edu",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "freshstack",
      "name": "FreshStack",
      "page": "https://rag-repo.org/source/freshstack",
      "category": "retrieval-benchmarks",
      "categoryName": "Retrieval benchmarks & evaluation",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "glaive-function-calling",
      "name": "Glaive Function Calling v2",
      "page": "https://rag-repo.org/source/glaive-function-calling",
      "category": "agentic-tool-use",
      "categoryName": "Agentic & Tool-Use",
      "version": "v2",
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "google-microsoft-open-buildings",
      "name": "Google-Microsoft-OSM Open Buildings (VIDA)",
      "page": "https://rag-repo.org/source/google-microsoft-open-buildings",
      "category": "geospatial",
      "categoryName": "Geospatial & mapping",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "legalbench-rag",
      "name": "LegalBench-RAG",
      "page": "https://rag-repo.org/source/legalbench-rag",
      "category": "retrieval-benchmarks",
      "categoryName": "Retrieval benchmarks & evaluation",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "nemotron-post-training-v2",
      "name": "Nemotron Post-Training Dataset v2",
      "page": "https://rag-repo.org/source/nemotron-post-training-v2",
      "category": "multilingual",
      "categoryName": "Multilingual & regional corpora",
      "version": "v2",
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "omat24",
      "name": "Open Materials 2024 (OMat24)",
      "page": "https://rag-repo.org/source/omat24",
      "category": "chemistry-materials",
      "categoryName": "Chemistry, materials & life sciences",
      "version": "2024",
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "openthoughts3",
      "name": "OpenThoughts3-1.2M",
      "page": "https://rag-repo.org/source/openthoughts3",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "rcsb-protein-data-bank",
      "name": "RCSB Protein Data Bank",
      "page": "https://rag-repo.org/source/rcsb-protein-data-bank",
      "category": "biomedical",
      "categoryName": "Biomedical & health",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "rteb",
      "name": "RTEB (Retrieval Embedding Benchmark)",
      "page": "https://rag-repo.org/source/rteb",
      "category": "retrieval-benchmarks",
      "categoryName": "Retrieval benchmarks & evaluation",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "structured-wikipedia",
      "name": "Structured Wikipedia",
      "page": "https://rag-repo.org/source/structured-wikipedia",
      "category": "encyclopaedic",
      "categoryName": "Encyclopaedic & general knowledge",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "synth-pleias",
      "name": "SYNTH",
      "page": "https://rag-repo.org/source/synth-pleias",
      "category": "encyclopaedic",
      "categoryName": "Encyclopaedic & general knowledge",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "t2-ragbench",
      "name": "T²-RAGBench",
      "page": "https://rag-repo.org/source/t2-ragbench",
      "category": "rag-benchmarks",
      "categoryName": "RAG-specific & evaluation",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "the-stack-v2",
      "name": "The Stack v2",
      "page": "https://rag-repo.org/source/the-stack-v2",
      "category": "code",
      "categoryName": "Code & technical documentation",
      "version": "v2",
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "huge",
      "supersedes": [
        "the-stack"
      ]
    },
    {
      "slug": "toolbench",
      "name": "ToolBench",
      "page": "https://rag-repo.org/source/toolbench",
      "category": "agentic-tool-use",
      "categoryName": "Agentic & Tool-Use",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "toucan-agentic",
      "name": "Toucan-1.5M",
      "page": "https://rag-repo.org/source/toucan-agentic",
      "category": "agentic-tool-use",
      "categoryName": "Agentic & Tool-Use",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "upstash-wikipedia-bge-m3",
      "name": "Upstash Wikipedia 2024 BGE-M3 Embeddings",
      "page": "https://rag-repo.org/source/upstash-wikipedia-bge-m3",
      "category": "embedded-datasets",
      "categoryName": "Pre-embedded & RAG-ready",
      "version": "2024-06",
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "weatherbench-2",
      "name": "WeatherBench 2",
      "page": "https://rag-repo.org/source/weatherbench-2",
      "category": "climate-earth",
      "categoryName": "Climate & earth observation",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "wikidata-embedding-project",
      "name": "Wikidata Embedding Project",
      "page": "https://rag-repo.org/source/wikidata-embedding-project",
      "category": "embedded-datasets",
      "categoryName": "Pre-embedded & RAG-ready",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "unknown",
      "supersedes": []
    },
    {
      "slug": "xlam-function-calling",
      "name": "xLAM Function-Calling (APIGen)",
      "page": "https://rag-repo.org/source/xlam-function-calling",
      "category": "agentic-tool-use",
      "categoryName": "Agentic & Tool-Use",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "limited",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "yodas2",
      "name": "YODAS2",
      "page": "https://rag-repo.org/source/yodas2",
      "category": "speech-audio",
      "categoryName": "Speech & audio",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "huge",
      "supersedes": []
    },
    {
      "slug": "zyda-2",
      "name": "Zyda-2",
      "page": "https://rag-repo.org/source/zyda-2",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": null,
      "lastReviewed": "2026-09-10",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "common-corpus",
      "name": "Common Corpus",
      "page": "https://rag-repo.org/source/common-corpus",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "common-pile",
      "name": "Common Pile v0.1",
      "page": "https://rag-repo.org/source/common-pile",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": "v0.1",
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "crag-benchmark",
      "name": "CRAG (Comprehensive RAG Benchmark)",
      "page": "https://rag-repo.org/source/crag-benchmark",
      "category": "rag-benchmarks",
      "categoryName": "RAG-specific & evaluation",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "emilia",
      "name": "Emilia",
      "page": "https://rag-repo.org/source/emilia",
      "category": "speech-audio",
      "categoryName": "Speech & audio",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "limited",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "financebench",
      "name": "FinanceBench",
      "page": "https://rag-repo.org/source/financebench",
      "category": "rag-benchmarks",
      "categoryName": "RAG-specific & evaluation",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "limited",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "fineweb2-hq",
      "name": "FineWeb2-HQ",
      "page": "https://rag-repo.org/source/fineweb2-hq",
      "category": "multilingual",
      "categoryName": "Multilingual & regional corpora",
      "version": "2-HQ",
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "frames-benchmark",
      "name": "FRAMES (Fact, Fetch, and Reason)",
      "page": "https://rag-repo.org/source/frames-benchmark",
      "category": "rag-benchmarks",
      "categoryName": "RAG-specific & evaluation",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "fred",
      "name": "FRED (Federal Reserve Economic Data)",
      "page": "https://rag-repo.org/source/fred",
      "category": "statistics-economics",
      "categoryName": "Statistics & economics",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "unknown",
      "supersedes": []
    },
    {
      "slug": "alphaearth-satellite-embedding",
      "name": "Google Satellite Embedding (AlphaEarth Foundations)",
      "page": "https://rag-repo.org/source/alphaearth-satellite-embedding",
      "category": "embedded-datasets",
      "categoryName": "Pre-embedded & RAG-ready",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "huge",
      "supersedes": []
    },
    {
      "slug": "granary",
      "name": "Granary",
      "page": "https://rag-repo.org/source/granary",
      "category": "speech-audio",
      "categoryName": "Speech & audio",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "huge",
      "supersedes": []
    },
    {
      "slug": "institutional-books",
      "name": "Institutional Books 1.0",
      "page": "https://rag-repo.org/source/institutional-books",
      "category": "books-literature",
      "categoryName": "Books & literature",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "limited",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "lematerial",
      "name": "LeMaterial (LeMat-Bulk)",
      "page": "https://rag-repo.org/source/lematerial",
      "category": "chemistry-materials",
      "categoryName": "Chemistry, materials & life sciences",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "major-tom",
      "name": "Major TOM",
      "page": "https://rag-repo.org/source/major-tom",
      "category": "embedded-datasets",
      "categoryName": "Pre-embedded & RAG-ready",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "huge",
      "supersedes": []
    },
    {
      "slug": "mleb",
      "name": "Massive Legal Embedding Benchmark (MLEB)",
      "page": "https://rag-repo.org/source/mleb",
      "category": "retrieval-benchmarks",
      "categoryName": "Retrieval benchmarks & evaluation",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "miriad",
      "name": "MIRIAD",
      "page": "https://rag-repo.org/source/miriad",
      "category": "biomedical",
      "categoryName": "Biomedical & health",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "mixturevitae",
      "name": "MixtureVitae",
      "page": "https://rag-repo.org/source/mixturevitae",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "nemotron-cc-v2",
      "name": "Nemotron-CC-v2",
      "page": "https://rag-repo.org/source/nemotron-cc-v2",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": "v2",
      "lastReviewed": "2026-08-17",
      "accessType": "limited",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "omnilingual-asr-corpus",
      "name": "Omnilingual ASR Corpus",
      "page": "https://rag-repo.org/source/omnilingual-asr-corpus",
      "category": "speech-audio",
      "categoryName": "Speech & audio",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "omol25",
      "name": "Open Molecules 2025 (OMol25)",
      "page": "https://rag-repo.org/source/omol25",
      "category": "chemistry-materials",
      "categoryName": "Chemistry, materials & life sciences",
      "version": "2025",
      "lastReviewed": "2026-08-17",
      "accessType": "limited",
      "sizeTier": "medium",
      "supersedes": []
    },
    {
      "slug": "open-targets",
      "name": "Open Targets Platform",
      "page": "https://rag-repo.org/source/open-targets",
      "category": "biomedical",
      "categoryName": "Biomedical & health",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "ragtruth",
      "name": "RAGTruth",
      "page": "https://rag-repo.org/source/ragtruth",
      "category": "rag-benchmarks",
      "categoryName": "RAG-specific & evaluation",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "refinecode",
      "name": "RefineCode (OpenCoder)",
      "page": "https://rag-repo.org/source/refinecode",
      "category": "code",
      "categoryName": "Code & technical documentation",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    },
    {
      "slug": "regulations-gov",
      "name": "Regulations.gov",
      "page": "https://rag-repo.org/source/regulations-gov",
      "category": "government",
      "categoryName": "Government & public sector",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "unknown",
      "supersedes": []
    },
    {
      "slug": "txt360",
      "name": "TxT360",
      "page": "https://rag-repo.org/source/txt360",
      "category": "web-corpora",
      "categoryName": "Web corpora",
      "version": null,
      "lastReviewed": "2026-08-17",
      "accessType": "open",
      "sizeTier": "large",
      "supersedes": []
    }
  ]
}