bawadou

AI Data Extractor — Data skill for Claude Code

Data community

Free open-source extractor for AI coding assistant chat histories.

How to install AI Data Extractor

This entry records only its repository, not the path inside it, so there is no exact command to give. Open bawadou/ai-data-extractor and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Data Extractor does

Free open-source extractor for AI coding assistant chat histories. Supports Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code, and more.

Alternatives in Data

  • LLM Redteam — LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil 4.5k ★
  • Global Stock Data — US stock market data for AI coding assistants — zero-auth, official sources 1.5k ★
  • AI Data Extraction — extract all your personal data history from cursor, codex, claude-code, windsurf, and trae 1.3k ★

README

AI Coding Assistant Data Extraction

Extract your **own local chat history** from AI coding assistants into a single, normalized JSONL format - for fine-tuning, personal analytics, or just backing up years of conversations before an app's local database gets cleared.

Features

Auto-discovers and extracts complete conversation history, including:

  • User messages & assistant responses
  • Code context (file paths, selections, snippets)
  • Code diffs / suggested edits, where the tool records them
  • Tool calls and their results
  • Timestamps, session IDs, project paths, model names - whatever each tool's storage actually contains

Supported sources

# Tool Storage Search location
1 Claude Code JSONL, one file per session ~/.claude/projects/**/*.jsonl
2 Codex CLI JSONL "rollout" files ~/.codex/sessions/**/rollout-*.jsonl
3 Cursor SQLite (state.vscdb) ~/…/Cursor/User/{global,workspace}Storage
4 Windsurf SQLite, undocumented schema (heuristic) ~/…/Windsurf/User/{global,workspace}Storage
5 Trae SQLite + JSONL, undocumented (heuristic) ~/…/Trae
6 Continue JSON, one file per session ~/.continue/sessions/*.json
7 Gemini CLI JSON, one file per chat ~/.gemini/tmp//chats/*.json
8 OpenCode JSON (session/message/part trees) ~/.local/share/opencode/storage/
9 Cline / Roo Code (new) JSON, one folder per task /User/globalStorage//tasks/
10 Aider (new) Markdown transcript per project /.aider.chat.history.md

Every script searches macOS, Linux, and Windows conventions (`~/Library/Application Support`, `~/.config`, `~/.local/share`, `%APPDATA%`, `%LOCALAPPDATA%`) automatically - you don't need to tell it which OS you're on.

Why Cline and Aider

They're two of the most-used AI coding tools th