5 packages found
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 comma
Run Claude in self-improving loops to optimize measurable goals.
Secure MCP server for safe AI-powered terminal access with risk analysis, sandboxing, logging, filesystem protection, an
AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents