{"adoption": {"forks": 423, "observed_at": "2026-08-28T04:07:50.698295+00:00", "stars": 3247}, "canonical_url": "https://ross.abutalabs.com/products/lakesoul", "card": {"archived": false, "artifact_type": "framework", "description": "LakeSoul is an end-to-end, realtime cloud-native Lakehouse framework for fast data ingestion, concurrent updates, incremental analytics, multimodal data processing and vector search — powering next-generation BI and AI workloads.", "domain": ["big-data", "databases", "analytics", "machine-learning"], "enriched": true, "function": ["database", "streaming", "etl", "vector-database", "search-engine", "serialization", "data-science"], "health_score": 95, "homepage": "https://lakesoul-io.github.io/", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["lakesoul-io/LakeSoul"], "name": "lakesoul-io/LakeSoul", "platform": ["jvm", "python", "rust", "cloud", "self-hosted"], "pushed_at": "2026-08-25T10:47:58+00:00", "repo": "lakesoul-io/LakeSoul", "stars": 3247, "tags": ["lakehouse", "table-format", "spark", "flink", "apache-arrow", "datafusion", "upsert", "acid-transactions", "cdc", "incremental-processing", "olap", "ray", "daft", "rust-core", "vector-search", "data-engineering", "real-time", "docker", "kubernetes", "linux", "macos"], "topics": ["lakehouse", "spark", "flink", "streaming", "postgresql", "rust", "sql", "huggingface", "python", "pytorch", "arrow", "datafusion", "vectorized", "velox", "gluten", "daft", "ray", "vector-search"], "urls": [], "use_cases": ["build a real-time lakehouse with streaming ingestion from Kafka and Flink CDC", "run concurrent upserts and incremental reads on data lake tables", "query lakehouse tables with SQL from Spark, Flink, Presto, or DuckDB", "prepare tabular training datasets for AI and PyTorch workloads", "perform vector search over lakehouse data", "unify batch and stream processing on one table format", "avoid stitching together separate catalogs, compaction services, and auth layers"], "what_it_is": "LakeSoul is a cloud-native, real-time lakehouse framework with a Rust-native core providing ACID table format, concurrent upserts, incremental reads, and vector search. It integrates with Spark, Flink, Presto, Ray, Daft, and DuckDB, with PostgreSQL-based metadata management and built-in compaction and RBAC.", "when_to_avoid": ["you only need a widely adopted table format with the broadest ecosystem support, such as Apache Iceberg", "your stack relies on engines not in LakeSoul's compatibility matrix", "you prefer a fully serverless managed warehouse over self-managed lakehouse infrastructure", "your workloads are small-scale and don't need lakehouse complexity"], "when_to_choose": ["you need a batteries-included lakehouse platform rather than just a table format", "you require high-concurrency writes with ACID guarantees and auto conflict resolution", "you want one Rust-native core shared consistently across Java, Python, and C++ engines", "you need real-time incremental pipelines on Hadoop or Kubernetes clusters", "you want built-in compaction, RBAC, and vector retrieval out of the box"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/lakesoul", "repo": "lakesoul-io/LakeSoul", "role": "main", "score": 82}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.698295+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:43:54.403546+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b5c5d8495aa781d344eae390faaff53ed50c8bee90c48a89b0829cf3cda0f6d2", "fetched_at": "2026-08-28T04:07:50.698295+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lakesoul-io/LakeSoul"}, {"content_hash": "69a022d69e2bd73b2245143f3085d418e94890f3abbd1e3d094484bf0f1cd96d", "fetched_at": "2026-08-29T09:37:04.849255+00:00", "kind": "homepage", "missing": false, "url": "https://lakesoul-io.github.io/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 49}, "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": 1709, "days_push": 8, "days_rel": 342, "gap_med": 1, "n_releases_24m": 4}, "score": 82, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}