Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
codeclaw
CLI for exporting Claude Code/Codex sessions to Hugging Face with privacy redaction, MCP memory, and share-ready dataset workflows.
10stars
2forks
Python
ai-agentsautomationclaude-codeclicodexdata-pipelinedatasetdeveloper-toolsfine-tuninghuggingfacellmlocal-ai
Quality signals
StaleNo testsNo CIThin docsNo licenseNew
AI summary
Auto-generated overview of what this skill does and when to reach for it.
CLI to turn AI coding sessions into privacy-safe, shareable training datasets with redaction, review gates, and MCP memory.
Use this when
- you want to export Claude Code/Codex sessions for fine-tuning
- you need to redact secrets/PII before sharing datasets
- you want to review exports locally before publishing
- you’re building a dataset for public Hugging Face release
- you need to track session history via MCP memory
Don't use when
- you only need raw logs without privacy controls
- you’re working with non-AI session data
- you can’t run background daemons or MCP servers
Capabilities
- exports Claude Code/Codex sessions to local or Hugging Face datasets
- redacts secrets/PII with regex + optional ML NER layer
- manual review gates before dataset publishing
- background watch daemon for incremental session sync
- MCP server for session memory search and stats
- immutable dataset snapshots with dedupe indexing
InstallMCP + SKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest ychampion/codeclawAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/codeclaw curl -fsSL https://raw.githubusercontent.com/ychampion/codeclaw/main/SKILL.md -o ~/.claude/skills/codeclaw/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
codeclaw — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt