Multi-agent AI consultation framework for Claude Code. Three MCP servers wrapping CLI tools (Codex, Gemini, Qwen) for parallel code review and problem-solving with fallback chains and error detection.
Bridge to local Ollama LLM server. Run Llama, Mistral, Qwen and other local models through MCP.
Provide seamless access to multiple premium AI models through OpenRouter with secure OAuth authentication and easy setup. Integrate effortlessly with MCP-compatible clients like Cursor and Claude Desk