{"adoption": {"forks": 151, "observed_at": "2026-08-28T04:05:18.513836+00:00", "stars": 1661}, "canonical_url": "https://ross.abutalabs.com/products/lotus-data-lotus", "card": {"archived": false, "artifact_type": "library", "description": "Optimized Agentic and LLM Bulk Processing Over Your Data", "domain": ["large-language-models", "data-science"], "enriched": true, "function": ["machine-learning", "llm-inference", "rag", "etl", "data-science", "agent-framework", "search-engine"], "health_score": 93, "homepage": "https://lotus-data.github.io", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["lotus-data/lotus"], "name": "lotus-data/lotus", "platform": ["python"], "pushed_at": "2026-07-03T22:55:38+00:00", "repo": "lotus-data/lotus", "stars": 1661, "tags": ["semantic-operators", "pandas", "llm-data-processing", "query-engine", "unstructured-data", "declarative-programming", "data-engineering", "natural-language-processing", "retrieval-augmented-generation", "ai-agents"], "topics": ["ai-data-processing", "data", "llm", "pandas", "python", "semantic-operators", "semantic-search", "unstructured-data", "llm-data-processing", "llm-document-processing", "agentic-data-processing"], "urls": [], "use_cases": ["classify or filter thousands of documents with natural language criteria", "extract structured fields from unstructured text at scale", "run an agent over every file in a codebase and summarize results", "build RAG pipelines over a document corpus", "score model outputs row by row with LLM-as-judge evals", "mine agent logs for failure modes", "fan out deep research over many papers and synthesize findings"], "what_it_is": "LOTUS is a Python library providing a Pandas-like API of LLM-powered semantic operators (map, filter, extract, aggregate, top-k) for bulk processing structured and unstructured datasets with agents and LLMs. It optimizes these declarative operations for higher accuracy and lower cost, with reported speedups up to 400x.", "when_to_avoid": ["you need simple single-prompt LLM calls without bulk dataset operations", "your data is small enough that direct API calls suffice", "you need a no-code GUI tool rather than a Python library", "you require strict deterministic transformations with no LLM nondeterminism"], "when_to_choose": ["you need to apply LLM reasoning across a large dataset or document collection", "you want a Pandas-like declarative API instead of writing per-row LLM prompts", "cost and latency of naive LLM bulk processing are too high", "you want to combine structured and unstructured data in one query pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/lotus-data-lotus", "repo": "lotus-data/lotus", "role": "main", "score": 83}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.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": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:18.513836+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:44:38.063618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71d37646986ac8eda558c322d6f03027979c7f488fbe05616d5c7cdd5e7dabc6", "fetched_at": "2026-08-28T04:05:18.513836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lotus-data/lotus"}, {"content_hash": "2f04d362eac0f500a46078d3ba0d4a3e2895f56477a51bba64ea63b20426eae2", "fetched_at": "2026-08-29T11:16:58.379307+00:00", "kind": "homepage", "missing": false, "url": "https://lotus-data.github.io"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 90, "longevity": 55, "rhythm": 91}, "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": 778, "days_push": 61, "days_rel": 61, "gap_med": 18, "n_releases_24m": 8}, "score": 83, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}