Kong/volcano-agent-sdk

项目介绍

Build agents that chain LLM reasoning with MCP tools. Mix OpenAI, Claude, Mistral in one workflow. Parallel execution, branching, loops. Native retries, streaming, and typed errors.

📚 Read the full documentation at volcano.dev →

LLM automatically picks which MCP tools to call based on your prompt. No manual routing needed.

Define specialized agents and let the coordinator autonomously delegate tasks. Like automatic tool selection, but for agents.

Ask questions about what your agent did. Use .summary() or .ask() instead of parsing JSON.

OpenAI, Anthropic, Mistral, Bedrock, Vertex, Azure. Switch providers per-step or globally.

Parallel execution, branching, loops, sub-agent…

摘自 github.com/Kong/volcano-agent-sdk