# 0xSero/ai-data-extraction

extract all your personal data history from cursor, codex, claude-code, windsurf, and trae

Repository: https://github.com/0xSero/ai-data-extraction
Canonical: https://ross.abutalabs.com/products/ai-data-extraction
Language: Python
License Family: other
Last push: 2026-08-19T20:12:00+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 20
- inputs: {"age_days": 290, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1257, forks 105 (observed 2026-08-28T04:04:09.403579+00:00)

## 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.

## 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

## 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

## 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

## Facets
- artifact type: cli-tool
- maturity: active
- function: data-science, etl, parser, json, developer-tools
- domain: developer-tools, machine-learning, privacy
- platform: windows, python, cli
- tags: ai-coding-assistants, conversation-history, data-extraction, training-data, cursor, claude-code, windsurf, codex, data-engineering, macos, linux

## Member repositories
- 0xSero/ai-data-extraction (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.403579+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:07:09.720404+00:00, confidence not recorded.
  - readme: https://github.com/0xSero/ai-data-extraction (fetched 2026-08-28T04:04:09.403579+00:00, sha f3bb339461b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.