Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

This repository contains documentation created to better understand the open project

Blitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.

Multi-workspace terminal aggregator with Claude Code AI integration

AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.

Nightly Claude Code CLI Decompile — Reverse Engineered & Rebuilt

공식 API에 없는 30+ 기능까지, 터미널과 AI에서 쓰세요. 토스증권 비공식 CLI·MCP.

Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. Evidence-first methodology prevents hollow writing through structured intermediate artifacts.

An MCP extension for Ghidra

Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video

🚀🪐🌕🌑☄️🛸 Opensource equivalent of Google's Antigravity