A framework-agnostic, git-native standard for defining AI agents

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.

Open-source, agent-agnostic RTL formal verification skill library for AI coding agents: JasperGold FPV, SVA, proof optimization, and TCL workflows for Claude Code, Codex, Gemini CLI, and Cursor.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)