{ "schema_version": "1.0.0", "verification_stage_contract": "bounded-workflow-v2", "generated_at": "2026-07-29T14:27:32Z", "build_id": "rr-20260729T142732Z-8d0d89fca708", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "points": [ { "id": "gh:opendataloader-project/opendataloader-pdf", "score": 8.5, "popularity": 27455.0, "stars": 27466, "momentum": 8.4, "score_components": { "usefulness": 8.8, "novelty": 7.9, "momentum": 8.4, "maturity": 9.1, "open_source_build_quality": 8.4, "evidence": 7.2, "commercial_workflow_potential": 9.6, "setup_ease": 7.1 }, "tier": "Gold", "verdict": "try_now", "risk": "conditional", "verification_stage": "discovered", "pricing_fingerprint": null, "pricing_summary": null, "pricing_facts": [], "pricing_checked_at": null, "pricing_stale": null, "version": null, "last_release_at": null, "last_release_url": null, "maintenance_status": "source_activity_not_yet_measured", "integration_fingerprint": null, "integration_count": 0, "integrations": [], "source_observed_at": null, "observation_source_url": null, "observation_extractor_version": null, "observation_refs": {}, "observed_fields": [ "integration_count", "integration_fingerprint", "integrations", "last_release_at", "maintenance_status", "momentum", "popularity", "pricing_checked_at", "pricing_facts", "pricing_fingerprint", "pricing_stale", "pricing_summary", "risk", "score", "score_components", "stars", "tier", "verdict", "verification_stage", "version" ], "date": "2026-07-19", "source_build_id": "rr-20260719T100820Z-9f68f20831d6" }, { "id": "gh:opendataloader-project/opendataloader-pdf", "score": 8.5, "popularity": 27455.0, "stars": 27531, "momentum": 8.4, "score_components": { "usefulness": 8.8, "novelty": 7.9, "momentum": 8.4, "maturity": 9.1, "open_source_build_quality": 8.4, "evidence": 7.2, "commercial_workflow_potential": 9.6, "setup_ease": 7.1 }, "tier": "Gold", "verdict": "try_now", "risk": "conditional", "verification_stage": "discovered", "pricing_fingerprint": null, "pricing_summary": null, "pricing_facts": [], "pricing_checked_at": null, "pricing_stale": null, "version": null, "last_release_at": null, "last_release_url": null, "maintenance_status": "source_activity_not_yet_measured", "integration_fingerprint": null, "integration_count": 0, "integrations": [], "source_observed_at": null, "observation_source_url": null, "observation_extractor_version": null, "observation_refs": {}, "observed_fields": [ "integration_count", "integration_fingerprint", "integrations", "last_release_at", "maintenance_status", "momentum", "popularity", "pricing_checked_at", "pricing_facts", "pricing_fingerprint", "pricing_stale", "pricing_summary", "risk", "score", "score_components", "stars", "tier", "verdict", "verification_stage", "version" ], "date": "2026-07-20", "source_build_id": "rr-20260720T231958Z-538b95791e5c" }, { "id": "gh:opendataloader-project/opendataloader-pdf", "score": 8.5, "popularity": 27455.0, "stars": 27580, "momentum": 8.4, "score_components": { "usefulness": 8.8, "novelty": 7.9, "momentum": 8.4, "maturity": 9.1, "open_source_build_quality": 8.4, "evidence": 7.2, "commercial_workflow_potential": 9.6, "setup_ease": 7.1 }, "tier": "Gold", "verdict": "try_now", "risk": "conditional", "verification_stage": "discovered", "pricing_fingerprint": null, "pricing_summary": null, "pricing_facts": [], "pricing_checked_at": null, "pricing_stale": null, "version": null, "last_release_at": null, "last_release_url": null, "maintenance_status": "source_activity_not_yet_measured", "integration_fingerprint": null, "integration_count": 0, "integrations": [], "source_observed_at": null, "observation_source_url": null, "observation_extractor_version": null, "observation_refs": {}, "observed_fields": [ "integration_count", "integration_fingerprint", "integrations", "last_release_at", "maintenance_status", "momentum", "popularity", "pricing_checked_at", "pricing_facts", "pricing_fingerprint", "pricing_stale", "pricing_summary", "risk", "score", "score_components", "stars", "tier", "verdict", "verification_stage", "version" ], "date": "2026-07-21", "source_build_id": "rr-20260721T100926Z-12d26cd1d0f0" }, { "id": "gh:opendataloader-project/opendataloader-pdf", "score": 8.5, "popularity": 27455.0, "stars": 27948, "momentum": 9.0, "score_components": { "usefulness": 8.8, "novelty": 7.9, "momentum": 8.4, "maturity": 9.1, "open_source_build_quality": 8.4, "evidence": 7.2, "commercial_workflow_potential": 9.6, "setup_ease": 7.1 }, "tier": "Gold", "verdict": "try_now", "risk": "conditional", "verification_stage": "discovered", "pricing_fingerprint": null, "pricing_summary": null, "pricing_facts": [], "pricing_checked_at": null, "pricing_stale": null, "version": "v2.5.0", "last_release_at": "2026-07-14T09:24:00Z", "last_release_url": "https://github.com/opendataloader-project/opendataloader-pdf/releases/tag/v2.5.0", "maintenance_status": "active", "integration_fingerprint": null, "integration_count": 0, "integrations": [], "source_observed_at": "2026-07-28T10:17:34.274766Z", "observation_source_url": "https://api.github.com/graphql", "observation_extractor_version": "github-observer-v2", "observation_refs": { "stars": "obs_f036f3a6f46ff7d2917239bd", "version": "obs_9d87874f43b966a71b2a7fa0", "last_release_at": "obs_4a1c3c2cba2d39d7ca2ae63c", "last_release_url": "obs_ad4dd2c0b2adcc1048703907", "pushed_at": "obs_49fbdf1a46177736aca04c91", "archived": "obs_89d4cd790c43b2c589f078cd", "default_branch": "obs_8cd448d34d746458ddac65d1", "default_branch_updated_at": "obs_107a8e8204765ccd4ee29dd8", "maintenance_status": "obs_452f63d5cf8f0fa421f49334", "momentum": "obs_7e93dd7f33787f7ece60b5bd", "repository_topics": "obs_3fcf8b79544f7d1de6e5f270", "integrations": "obs_78072f8c413c1ba9eae51dfa", "integration_fingerprint": "obs_fc3930534552a6335615facc", "deployment_models": "obs_5c344a8e72e1133f859b2344", "extensibility": "obs_dc2febfe6f52530469dff342" }, "observed_fields": [ "integration_count", "integration_fingerprint", "integrations", "last_release_at", "maintenance_status", "momentum", "popularity", "pricing_checked_at", "pricing_facts", "pricing_fingerprint", "pricing_stale", "pricing_summary", "risk", "score", "score_components", "stars", "tier", "verdict", "verification_stage", "version" ], "date": "2026-07-28", "source_build_id": "rr-20260728T10173427476-cba0cd6243c7" }, { "id": "gh:opendataloader-project/opendataloader-pdf", "score": 8.5, "popularity": 27455.0, "stars": 27985, "momentum": 9.6, "score_components": { "usefulness": 8.8, "novelty": 7.9, "momentum": 8.4, "maturity": 9.1, "open_source_build_quality": 8.4, "evidence": 7.2, "commercial_workflow_potential": 9.6, "setup_ease": 7.1 }, "tier": "Gold", "verdict": "try_now", "risk": "conditional", "verification_stage": "discovered", "pricing_fingerprint": null, "pricing_summary": null, "pricing_facts": [], "pricing_checked_at": null, "pricing_stale": null, "version": "v2.5.0", "last_release_at": "2026-07-14T09:24:00Z", "last_release_url": "https://github.com/opendataloader-project/opendataloader-pdf/releases/tag/v2.5.0", "maintenance_status": "active", "integration_fingerprint": null, "integration_count": 0, "integrations": [], "source_observed_at": "2026-07-29T10:17:05.832710Z", "observation_source_url": "https://api.github.com/graphql", "observation_extractor_version": "github-observer-v2", "observation_refs": { "stars": "obs_aaa9b93afe648a48c36ee40d", "version": "obs_5b26568689b4635a0b63e844", "last_release_at": "obs_2f16b4ec9dd5d4e55fed2504", "last_release_url": "obs_22670667a7cf3359dff0783a", "pushed_at": "obs_38bfc6e932442b32c3a6c128", "archived": "obs_e005bbc4997886c9e13014e4", "default_branch": "obs_04329ec4de7b74fc6ac45106", "default_branch_updated_at": "obs_f7ee1d817933971eee7eeace", "maintenance_status": "obs_59e74e95b34842da23bfe28e", "momentum": "obs_221f1fd09a994eb83592e398", "repository_topics": "obs_bdb4a5eff66ea0db4e14cd80", "integrations": "obs_7ff4b06e7f9a98a6a2c3580e", "integration_fingerprint": "obs_753b1dbf19f8887b01c93483", "deployment_models": "obs_361cc1439e5a6823d7b2a05e", "extensibility": "obs_225da4bbddea3b997798dff9" }, "observed_fields": [ "integration_count", "integration_fingerprint", "integrations", "last_release_at", "maintenance_status", "momentum", "popularity", "pricing_checked_at", "pricing_facts", "pricing_fingerprint", "pricing_stale", "pricing_summary", "risk", "score", "score_components", "stars", "tier", "verdict", "verification_stage", "version" ], "date": "2026-07-29", "source_build_id": "rr-20260729T142732Z-8d0d89fca708" } ], "changes": [ { "id": "evt_b12c5f11c2321bae41b1", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-29T10:17:05.832710Z", "before": 27948, "after": 27985, "explanation": "Stars changed: 27948 → 27985.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_fb77c8dfb762bc083b86", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-28T10:17:34.274766Z", "before": 27941, "after": 27948, "explanation": "Source-observed stars changed: 27941 → 27948. This reports the retained observation delta and does not infer why the upstream change occurred.", "explanation_scope": "source_observation_delta", "evidence_refs": { "after_observation_id": "obs_f036f3a6f46ff7d2917239bd", "after_observed_at": "2026-07-28T10:17:34.274766Z", "after_source_path": "repository.stargazerCount", "before_observation_id": "obs_ec085135a83b3da262c8f520", "before_observed_at": "2026-07-28T07:11:06.213377Z", "before_source_path": "repository.stargazerCount", "entity_source_url": "https://github.com/opendataloader-project/opendataloader-pdf", "extractor_version": "github-observer-v2", "field": "stars", "source_url": "https://api.github.com/graphql" }, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_6779fa99956405f06d55", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "version_changed", "occurred_at": "2026-07-28T07:11:06.213377Z", "before": null, "after": "v2.5.0", "explanation": "Version changed: not recorded → v2.5.0.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_55e276c1a9256a2e4e86", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "maintenance_changed", "occurred_at": "2026-07-28T07:11:06.213377Z", "before": "source_activity_not_yet_measured", "after": "active", "explanation": "Maintenance changed: source_activity_not_yet_measured → active.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_0495843e708d87302809", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-28T07:11:06.213377Z", "before": 27580, "after": 27941, "explanation": "Stars changed: 27580 → 27941.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_d48693c13e7276cf1ac0", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T10:09:26Z", "before": 27578, "after": 27580, "explanation": "Stars changed: 27578 → 27580.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_02e70692e140b82cfbb5", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T08:19:02Z", "before": 27567, "after": 27578, "explanation": "Stars changed: 27567 → 27578.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_d8e57be4325e9b20e7e8", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T07:06:25Z", "before": 27557, "after": 27567, "explanation": "Stars changed: 27557 → 27567.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_3f2ab5fc70622a976616", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T06:07:09Z", "before": 27550, "after": 27557, "explanation": "Stars changed: 27550 → 27557.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_a52e98219220be488412", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T05:11:59Z", "before": 27544, "after": 27550, "explanation": "Stars changed: 27544 → 27550.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_a78b10721139e93f7533", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T03:08:18Z", "before": 27533, "after": 27544, "explanation": "Stars changed: 27533 → 27544.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_dfc4463605a63392f7ca", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T01:03:35Z", "before": 27532, "after": 27533, "explanation": "Stars changed: 27532 → 27533.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_194a1e4c4bfa6ec5027a", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-21T00:08:05Z", "before": 27531, "after": 27532, "explanation": "Stars changed: 27531 → 27532.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_aa6efcdc48bc305fb527", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-20T23:19:58Z", "before": 27525, "after": 27531, "explanation": "Stars changed: 27525 → 27531.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_cc2d2f99a603e73251a9", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-20T22:07:10Z", "before": 27522, "after": 27525, "explanation": "Stars changed: 27522 → 27525.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_30407f732bac7252b429", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-20T20:04:55Z", "before": 27520, "after": 27522, "explanation": "Stars changed: 27520 → 27522.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_c34bd055a53602ad1751", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-20T19:06:00Z", "before": 27516, "after": 27520, "explanation": "Stars changed: 27516 → 27520.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_a8d6320d29f80415e152", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-20T17:03:24Z", "before": 27468, "after": 27516, "explanation": "Stars changed: 27468 → 27516.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_efd3eda00a985ceef092", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-20T16:07:26Z", "before": 27466, "after": 27468, "explanation": "Stars changed: 27466 → 27468.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_a993788ab399003b2488", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-19T09:07:03Z", "before": 27465, "after": 27466, "explanation": "Stars changed: 27465 → 27466.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_4dc356be4b119251005f", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-19T08:06:52Z", "before": 27460, "after": 27465, "explanation": "Stars changed: 27460 → 27465.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_844f51285a193c93f642", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-19T05:06:08Z", "before": 27459, "after": 27460, "explanation": "Stars changed: 27459 → 27460.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_573734cb3a59248b0969", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-19T04:07:24Z", "before": 27458, "after": 27459, "explanation": "Stars changed: 27458 → 27459.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_6f7ab1105d7c7380e7ba", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "stars_changed", "occurred_at": "2026-07-19T03:06:09Z", "before": 27455, "after": 27458, "explanation": "Stars changed: 27455 → 27458.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false }, { "id": "evt_c4cb88e2ad22ad83a5ca", "entity_id": "gh:opendataloader-project/opendataloader-pdf", "item_url": "/item/opendataloader-project-opendataloader-pdf/", "title": "opendataloader-project/opendataloader-pdf", "category": "other", "kind": "new_entity", "occurred_at": "2026-07-19T01:06:36Z", "before": null, "after": "try_now", "explanation": "Newly added to RepoRadar's decision catalog.", "explanation_scope": "catalog_snapshot_delta", "evidence_refs": {}, "tier": "Gold", "risk": "conditional", "verdict": "try_now", "score": 8.5, "entity_kind": "open_source", "verification_stage": "discovered", "type": "GitHub repo", "section": "Document parsing", "local_ai": false, "local_model_compatible": false, "discovery_topic": "data_tooling", "discovery_topic_status": "unreviewed", "setup_ease": 7.1, "best_for": [ "teams building RAG or document-ingestion pipelines around PDFs", "developers who need structured extraction with boxes, tables, and OCR instead of plain-text PDF scraping" ], "risk_categories": [], "search_text": "opendataloader-project/opendataloader-pdf opendataloader-project open_source other gold conditional try_now teams building rag or document-ingestion pipelines around pdfs developers who need structured extraction with boxes, tables, and ocr instead of plain-text pdf scraping", "material_mover": false } ] }