{
  "feed": "RAG Repo - recently added and reviewed sources",
  "site": "https://rag-repo.org",
  "generated": "2026-09-18",
  "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": "achievement-standards-network",
      "name": "Achievement Standards Network",
      "page": "https://rag-repo.org/source/achievement-standards-network",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "agieval",
      "name": "AGIEval",
      "page": "https://rag-repo.org/source/agieval",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": "1.1",
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "big-math-rl-verified",
      "name": "Big-Math-RL-Verified",
      "page": "https://rag-repo.org/source/big-math-rl-verified",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "bridge-math-remediation",
      "name": "Bridge (Remediating Math Mistakes)",
      "page": "https://rag-repo.org/source/bridge-math-remediation",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "cefr-descriptors",
      "name": "CEFR Companion Volume Descriptors",
      "page": "https://rag-repo.org/source/cefr-descriptors",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": "2020 Companion Volume",
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "cefr-j-english-profile",
      "name": "CEFR-J English Profiles (Open Language Profiles)",
      "page": "https://rag-repo.org/source/cefr-j-english-profile",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": "Wordlist 1.6 (2020)",
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "clear-corpus",
      "name": "CLEAR Corpus (CommonLit Ease of Readability)",
      "page": "https://rag-repo.org/source/clear-corpus",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "curriculum-for-excellence",
      "name": "Curriculum for Excellence (Scotland)",
      "page": "https://rag-repo.org/source/curriculum-for-excellence",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "ednet",
      "name": "EdNet",
      "page": "https://rag-repo.org/source/ednet",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "eedi-mining-misconceptions",
      "name": "Eedi - Mining Misconceptions in Mathematics",
      "page": "https://rag-repo.org/source/eedi-mining-misconceptions",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "limited",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "junyi-academy",
      "name": "Junyi Academy Online Learning Activity Dataset",
      "page": "https://rag-repo.org/source/junyi-academy",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "mrac-australian-curriculum",
      "name": "Machine Readable Australian Curriculum (MRAC)",
      "page": "https://rag-repo.org/source/mrac-australian-curriculum",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": "9.0",
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "mathdial",
      "name": "MathDial",
      "page": "https://rag-repo.org/source/mathdial",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "mathtutorbench",
      "name": "MathTutorBench",
      "page": "https://rag-repo.org/source/mathtutorbench",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "mmlu-pro",
      "name": "MMLU-Pro",
      "page": "https://rag-repo.org/source/mmlu-pro",
      "category": "rag-benchmarks",
      "categoryName": "RAG-specific & evaluation",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "numinamath",
      "name": "NuminaMath",
      "page": "https://rag-repo.org/source/numinamath",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "omni-math",
      "name": "Omni-MATH",
      "page": "https://rag-repo.org/source/omni-math",
      "category": "mathematics",
      "categoryName": "Mathematics & reasoning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "onestopenglish",
      "name": "OneStopEnglish Corpus",
      "page": "https://rag-repo.org/source/onestopenglish",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "phet-interactive-simulations",
      "name": "PhET Interactive Simulations",
      "page": "https://rag-repo.org/source/phet-interactive-simulations",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "unknown",
      "supersedes": []
    },
    {
      "slug": "pslc-datashop",
      "name": "PSLC DataShop",
      "page": "https://rag-repo.org/source/pslc-datashop",
      "category": "data-platforms",
      "categoryName": "Data platforms & marketplaces",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "limited",
      "sizeTier": "unknown",
      "supersedes": []
    },
    {
      "slug": "scienceqa",
      "name": "ScienceQA",
      "page": "https://rag-repo.org/source/scienceqa",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "slug": "simple-english-wikipedia",
      "name": "Simple English Wikipedia",
      "page": "https://rag-repo.org/source/simple-english-wikipedia",
      "category": "encyclopaedic",
      "categoryName": "Encyclopaedic & general knowledge",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "tatoeba",
      "name": "Tatoeba",
      "page": "https://rag-repo.org/source/tatoeba",
      "category": "multilingual",
      "categoryName": "Multilingual & regional corpora",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "new-zealand-curriculum",
      "name": "The New Zealand Curriculum (Tahurangi)",
      "page": "https://rag-repo.org/source/new-zealand-curriculum",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "ontario-curriculum",
      "name": "The Ontario Curriculum",
      "page": "https://rag-repo.org/source/ontario-curriculum",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "tiny",
      "supersedes": []
    },
    {
      "slug": "wikibooks",
      "name": "Wikibooks",
      "page": "https://rag-repo.org/source/wikibooks",
      "category": "education",
      "categoryName": "Education & open learning",
      "version": null,
      "lastReviewed": "2026-09-17",
      "accessType": "open",
      "sizeTier": "small",
      "supersedes": []
    },
    {
      "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": []
    }
  ]
}