Home: capabilities, use cases, and sources

Enterprise-grade distributed service mesh for MCP agents. Distributed Dynamic Dependency Injection (DDDI) with zero-boilerplate, Kubernetes-native deployment across Python, TypeScript, and Java. Key features: +claude means prefer the reasoning agent, 02 THINK Reasoning picks its own collaborators, A --raw mode turns your AI coding assistant into a mesh expert, and a ten-day tutorial ships inside the CLI, a hundred more arrive through LiteLLM, the Vercel AI SDK, or Spring AI, A provider agent advertises llm, and that is the whole integration, Add a new agent to the mesh tomorrow and the model can reach it — with no redeploy and no change to this code, agent(name="claude-weather", auto_run=True) class Agent: pass The LLM orchestrates tools via the mesh filter pattern and returns a typed pydantic Forecast — no agentic loop to write, agent(name="trip-planner", auto_run=True) class TripAgent: pass io.