volcano-agent-sdk
by Kong·★ 392·Score 49
TypeScript SDK for building AI agents that combine LLM reasoning with MCP tools, supporting multiple providers and advanced patterns.
Overview
Volcano Agent SDK is a comprehensive TypeScript framework for creating sophisticated AI agents that can seamlessly integrate Large Language Model reasoning with real-world actions through MCP tools. It supports multiple LLM providers including OpenAI, Anthropic, and Mistral, allowing developers to mix different models within a single workflow. The SDK features advanced patterns like parallel execution, branching, loops, and sub-agent composition, making it suitable for complex multi-agent systems.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this SDK when building complex multi-agent workflows with specialized roles that need to coordinate through MCP tools, especially when working with multiple LLM providers in a single application.
When NOT to choose this
Avoid this if you need a simpler agent framework without multi-agent coordination capabilities or if you're looking for a solution with extensive built-in tools rather than MCP integration.
Comparable tools
Installation
npm install @volcano.dev/agentFor Claude Desktop integration, add to your claude_desktop_config.json:
{
"mcpServers": {
"volcano-agent": {
"command": "npx",
"args": ["@volcano.dev/agent", "server"]
}
}
}FAQ
- What LLM providers does Volcano Agent SDK support?
- The SDK supports OpenAI, Anthropic, Mistral, Llama, Bedrock, Vertex, and Azure. You can switch providers per-step or globally within a workflow.
- How does the automatic tool selection feature work?
- The LLM automatically determines which MCP tools to call based on your prompt, eliminating the need for manual routing. You simply provide the available MCP tools, and the intelligent agent selects the appropriate ones.
Compare volcano-agent-sdk with
Last updated · Auto-generated from public README + GitHub signals.