{"adoption": {"forks": 105, "observed_at": "2026-08-28T04:04:09.403579+00:00", "stars": 1257}, "canonical_url": "https://ross.abutalabs.com/products/ai-data-extraction", "card": {"archived": false, "artifact_type": "cli-tool", "description": "extract all your personal data history from cursor, codex, claude-code, windsurf, and trae", "domain": ["developer-tools", "machine-learning", "privacy"], "enriched": true, "function": ["data-science", "etl", "parser", "json", "developer-tools"], "health_score": 79, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["0xSero/ai-data-extraction"], "name": "0xSero/ai-data-extraction", "platform": ["windows", "python", "cli"], "pushed_at": "2026-08-19T20:12:00+00:00", "repo": "0xSero/ai-data-extraction", "stars": 1257, "tags": ["ai-coding-assistants", "conversation-history", "data-extraction", "training-data", "cursor", "claude-code", "windsurf", "codex", "data-engineering", "macos", "linux"], "topics": [], "urls": [], "use_cases": ["export my cursor chat history", "extract claude code conversations for training data", "backup ai coding assistant sessions", "build a dataset from ai assistant chats", "migrate conversation history between ai coding tools", "analyze my ai assistant usage locally"], "what_it_is": "A Python toolkit of extraction scripts that pulls complete chat, agent, and code-context history from AI coding assistants like Cursor, Claude Code, Codex, Windsurf, Trae, Continue, Gemini CLI, and OpenCode. It reads local JSONL, JSON, and SQLite storage to produce structured datasets suitable for machine learning training.", "when_to_avoid": ["you need a GUI or hosted service rather than local Python scripts", "you want real-time syncing of assistant data instead of one-off extraction", "the repository has no license, so reuse/redistribution terms are unclear"], "when_to_choose": ["you want to export or back up your local AI coding assistant conversation history", "you need structured chat/code-context data for ML training or analysis", "you use multiple assistants (Cursor, Claude Code, Windsurf, etc.) and want one toolkit"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ai-data-extraction", "repo": "0xSero/ai-data-extraction", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:09.403579+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:07:09.720404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f3bb339461b472a639d10d081a6c532055be7d50748fd5dbac8fc8aaafe889c6", "fetched_at": "2026-08-28T04:04:09.403579+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/ai-data-extraction"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 20, "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": 290, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}