ychampion/codeclaw

CLI for exporting Claude Code/Codex sessions to Hugging Face with privacy redaction, MCP memory, and share-ready dataset workflows.

48
/ 100
Emerging

This tool helps AI engineers and machine learning practitioners turn their daily coding interactions with large language models like Claude Code and Codex into structured, privacy-safe datasets. It takes raw conversational sessions and transforms them into clean, redacted training data, ready for building and refining custom AI models. The output is a secure, shareable dataset suitable for fine-tuning or analysis, with robust privacy controls.

Available on PyPI.

Use this if you want to create valuable training datasets from your coding assistant conversations, ensuring sensitive information is removed and data quality is high.

Not ideal if you are looking for a general-purpose code management tool or a simple session logger without the need for dataset creation or privacy features.

AI-engineering ML-data-preparation LLM-fine-tuning privacy-compliance software-development
Maintenance 10 / 25
Adoption 5 / 25
Maturity 20 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Python

License

MIT

Last pushed

Feb 26, 2026

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/ychampion/codeclaw"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.