{"adoption": {"forks": 132, "observed_at": "2026-08-28T04:05:15.378737+00:00", "stars": 1642}, "canonical_url": "https://ross.abutalabs.com/products/persona-hub", "card": {"archived": false, "artifact_type": "dataset", "description": "Official repo for the paper \"Scaling Synthetic Data Creation with 1,000,000,000 Personas\"", "domain": ["large-language-models", "machine-learning", "data-science", "artificial-intelligence"], "enriched": true, "function": ["data-generation", "llm-training", "prompt-engineering", "rag"], "health_score": 24, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["tencent-ailab/persona-hub"], "name": "tencent-ailab/persona-hub", "platform": ["python"], "pushed_at": "2025-02-19T06:37:09+00:00", "repo": "tencent-ailab/persona-hub", "stars": 1642, "tags": ["synthetic-data", "personas", "llm-datasets", "data-synthesis", "research"], "topics": [], "urls": [], "use_cases": ["generate synthetic training data for LLM fine-tuning", "create diverse math and reasoning problems at scale", "synthesize instructions and user prompts with LLMs", "generate game NPCs and tool/function definitions", "curate diverse personas for data augmentation"], "what_it_is": "PersonaHub is Tencent AI Lab's collection of 1 billion diverse personas plus code for persona-driven synthetic data creation with LLMs. It includes released persona subsets (200k preview, 370M elite personas) and synthetic data samples like math problems, instructions, and game NPCs.", "when_to_avoid": ["you need a permissively licensed dataset for commercial use (data is CC BY-NC-SA)", "you need production-ready software rather than research code", "you need small-scale, human-curated data"], "when_to_choose": ["you need large-scale diverse synthetic data for LLM training", "you want persona-driven diversity in generated datasets", "you need ready-made math, reasoning, or instruction datasets"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/persona-hub", "repo": "tencent-ailab/persona-hub", "role": "main", "score": 27}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:15.378737+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:46:21.349788+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfb08ed586ddbe80da7eeda0081d447592f68d34d87a907ca0df610558babd3", "fetched_at": "2026-08-28T04:05:15.378737+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tencent-ailab/persona-hub"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 7, "longevity": 57, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 803, "days_push": 560, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 27, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}