{"adoption": {"forks": 196, "observed_at": "2026-08-28T04:04:22.346409+00:00", "stars": 1324}, "canonical_url": "https://ross.abutalabs.com/products/paperguru-benchmark", "card": {"archived": false, "artifact_type": "dataset", "description": "Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB", "domain": ["artificial-intelligence", "large-language-models", "education"], "enriched": true, "function": ["benchmarking", "rag", "llm-inference", "agent-framework", "data-science"], "health_score": 72, "homepage": null, "language": "TeX", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["AutoTrustAI/PaperGuru-Benchmark"], "name": "AutoTrustAI/PaperGuru-Benchmark", "platform": ["python", "cross-platform"], "pushed_at": "2026-06-08T21:14:07+00:00", "repo": "AutoTrustAI/PaperGuru-Benchmark", "stars": 1324, "tags": ["long-horizon-agents", "lifecycle-aware-memory", "paperbench", "surveybench", "academic-research", "evaluation-benchmark", "memory-systems", "ai-agents", "retrieval-augmented-generation", "research"], "topics": [], "urls": [], "use_cases": ["evaluate long-term memory systems for LLM agents", "benchmark agents on long-horizon research tasks like paper reproduction", "compare memory architectures against PaperBench and SurveyBench baselines", "research lifecycle-aware memory for multi-step agent workflows", "reproduce figures and results from the PaperGuru papers", "study agent performance on academic survey generation"], "what_it_is": "PaperGuru is a benchmark and research repository for Lifecycle-Aware Memory (LAM), a long-term memory primitive for long-horizon LLM agents, reporting state-of-the-art results on PaperBench (66.05%) and SurveyBench (94.66%). The repository contains benchmark materials, papers, and figure-reproduction assets written largely in TeX.", "when_to_avoid": ["you need a production-ready memory library or SDK to drop into your app", "you want a simple plug-and-play vector store or RAG tool", "you need a permissively licensed codebase (license is unclear/NOASSERTION)"], "when_to_choose": ["you need rigorous benchmarks for long-horizon LLM agent memory", "you are researching memory primitives for multi-step agents", "you want to compare your agent against published PaperBench/SurveyBench results"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/paperguru-benchmark", "repo": "AutoTrustAI/PaperGuru-Benchmark", "role": "main", "score": 53}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:22.346409+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:46:40.156441+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2432cc7a2787f282712f23d91592b2bb5975a2e89871bdb499349b0b126d64d", "fetched_at": "2026-08-28T04:04:22.346409+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AutoTrustAI/PaperGuru-Benchmark"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 86, "longevity": 8, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 117, "days_push": 86, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 53, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}