0xSero/ai-data-extraction

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1257 stars · 105 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

cli-tool · maturity active

data-science etl parser json developer-tools developer-tools machine-learning privacy windows python cli ai-coding-assistants conversation-history data-extraction training-data cursor claude-code windsurf codex data-engineering macos linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="0xSero/ai-data-extraction")