Skip to content
Back to search

volcano-agent-sdk

πŸŒ‹ Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools β€” in just a few lines of TypeScript.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/kong--volcano-agent-sdk/badge.svg)](/listings/kong--volcano-agent-sdk)

HTML

<a href="/listings/kong--volcano-agent-sdk"><img src="/api/listings/kong--volcano-agent-sdk/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Installation

npm install @volcano.dev/agent

That's it! Includes MCP support and all common LLM providers (OpenAI, Anthropic, Mistral, Llama, Vertex).

**[View installation guide β†’](https://volcano.dev/docs#installation)**

Hello World with Automatic Tool Selection

import { agent, llmOpenAI, mcp } from "@volcano.dev/agent";

const llm = llmOpenAI({ 
  apiKey: process.env.OPENAI_API_KEY!, 
  model: "gpt-4o-mini" 
});

const weather = mcp("http://localhost:8001/mcp");
const tasks = mcp("http://localhost:8002/mcp");

// Agent automatically picks the right tools
const results = await agent({ llm })
  .then({ 
    prompt: "What's the weather in Seattle? If it will rain, create a task to bring an umbrella",
    mcps: [weather, tasks]  // LLM chooses which tools to call
  })
  .run();

// Ask questions about what happened
const summary = await results.summary(llm);
console.log(summary);

Multi-Agent Coordinator

import { agent, llmOpenAI } from "@volcano.dev/agent";

const llm = llmOpenAI({ apiKey: process.env.OPENAI_API_KEY! });

// Define specialized agents
const researcher = agent({ llm, name: 'researcher', description: 'Finds facts and data' })
  .then({ prompt: "Research the topic." })
  .then({ prompt: "Summarize the research." });

const writer = agent({ llm, name: 'writer', description: 'Creates content' })
  .then({ prompt: "Write content." });

// Coordinator autonomously delegates to specialists
const results = await agent({ llm })
  .then({
    prompt: "Write a blog post about quantum computing",
    agents: [researcher, writer]  // Coordinator decides when done
  })
  .run();

// Ask what happened
const post = await results.ask(llm, "Show me the final blog post");
console.log(post);

**[View more examples β†’](https://volcano.dev/docs/examples)**

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md Β· README Β· 174 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. [![CI](https://github.com/Kong/volcano-agent-sdk/actions/workflows/ci.yml/badge.svg)](https://github.com/Kong/volcano-agent-sdk/actions/workflows/ci.yml)
  2. [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
  3. [![npm](https://img.shields.io/npm/v/@volcano.dev/agent.svg)](https://www.npmjs.com/package/@volcano.dev/agent)
  4. # πŸŒ‹ Volcano Agent SDK
  5. **The TypeScript SDK for Multi-Provider AI Agents**
  6. 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.
  7. πŸ“š **[Read the full documentation at volcano.dev β†’](https://volcano.dev/)**
  8. ## ✨ Features
  9. <table>
  10. <tr>
  11. <td width="33%">
  12. ### πŸ€– Automatic Tool Selection
  13. LLM automatically picks which MCP tools to call based on your prompt. No manual routing needed.
  14. </td>
  15. <td width="33%">
  16. ### 🧩 Multi-Agent Crews
  17. Define specialized agents and let the coordinator autonomously delegate tasks. Like automatic tool selection, but for agents.
  18. </td>
  19. <td width="33%">
  20. ### πŸ’¬ Conversational Results
  21. Ask questions about what your agent did. Use `.summary()` or `.ask()` instead of parsing JSON.
  22. </td>
  23. </tr>
  24. <tr>
  25. <td width="33%">
  26. ### πŸ”§ 100s of Models
  27. OpenAI, Anthropic, Mistral, Bedrock, Vertex, Azure. Switch providers per-step or globally.
  28. </td>
  29. <td width="33%">
  30. ### πŸ”„ Advanced Patterns
  31. Parallel execution, branching, loops, sub-agent composition. Enterprise-grade workflow control.
  32. </td>
  33. <td width="33%">
  34. ### πŸ“‘ Streaming
  35. Stream tokens in real-time as LLMs generate them. Perfect for chat UIs and SSE endpoints.
  36. </td>
  37. </tr>
  38. <tr>
  39. <td width="33%">
  40. ### πŸ›‘οΈ TypeScript-First
  41. Full type safety with IntelliSense. Catch errors before runtime.
  42. </td>
  43. <td width="33%">
  44. ### πŸ“Š Observability
  45. OpenTelemetry traces and metrics. Export to Jaeger, Prometheus, DataDog, or any OTLP backend.
  46. </td>
  47. <td width="33%">
  48. ### ⚑ Production-Ready
  49. Built-in retries, timeouts, error handling, and connection pooling. Battle-tested at scale.
  50. </td>
  51. </tr>
  52. </table>
  53. **[Explore all features β†’](https://volcano.dev/docs#key-features)**
  54. ## Quick Start
  55. ### Installation
  56. ```bash
  57. npm install @volcano.dev/agent
  58. ```
  59. That's it! Includes MCP support and all common LLM providers (OpenAI, Anthropic, Mistral, Llama, Vertex).
  60. **[View installation guide β†’](https://volcano.dev/docs#installation)**
  61. ### Hello World with Automatic Tool Selection
  62. ```ts
  63. import { agent, llmOpenAI, mcp } from "@volcano.dev/agent";
  64. const llm = llmOpenAI({
  65. apiKey: process.env.OPENAI_API_KEY!,
  66. model: "gpt-4o-mini"
  67. });
  68. const weather = mcp("http://localhost:8001/mcp");
  69. const tasks = mcp("http://localhost:8002/mcp");
  70. // Agent automatically picks the right tools
  71. const results = await agent({ llm })
  72. .then({
  73. prompt: "What's the weather in Seattle? If it will rain, create a task to bring an umbrella",
  74. mcps: [weather, tasks] // LLM chooses which tools to call
  75. })
  76. .run();
  77. // Ask questions about what happened
  78. const summary = await results.summary(llm);
  79. console.log(summary);
  80. ```
  81. ### Multi-Agent Coordinator
  82. ```ts
  83. import { agent, llmOpenAI } from "@volcano.dev/agent";
  84. const llm = llmOpenAI({ apiKey: process.env.OPENAI_API_KEY! });
  85. // Define specialized agents
  86. const researcher = agent({ llm, name: 'researcher', description: 'Finds facts and data' })
  87. .then({ prompt: "Research the topic." })
  88. .then({ prompt: "Summarize the research." });
  89. const writer = agent({ llm, name: 'writer', description: 'Creates content' })
  90. .then({ prompt: "Write content." });
  91. // Coordinator autonomously delegates to specialists
  92. const results = await agent({ llm })
  93. .then({
  94. prompt: "Write a blog post about quantum computing",
  95. agents: [researcher, writer] // Coordinator decides when done
  96. })
  97. .run();
  98. // Ask what happened
  99. const post = await results.ask(llm, "Show me the final blog post");
  100. console.log(post);
  101. ```
  102. **[View more examples β†’](https://volcano.dev/docs/examples)**
  103. ## Documentation
  104. ### πŸ“– Comprehensive Guides
  105. - **[Getting Started](https://volcano.dev/docs)** - Installation, quick start, core concepts
  106. - **[LLM Providers](https://volcano.dev/docs/providers)** - OpenAI, Anthropic, Mistral, Llama, Bedrock, Vertex, Azure
  107. - **[MCP Tools](https://volcano.dev/docs/mcp-tools)** - Automatic selection, OAuth authentication, connection pooling
  108. - **[Advanced Patterns](https://volcano.dev/docs/patterns)** - Parallel, branching, loops, multi-LLM workflows
  109. - **[Features](https://volcano.dev/docs/features)** - Streaming, retries, timeouts, hooks, error handling
  110. - **[Observability](https://volcano.dev/docs/observability)** - OpenTelemetry traces and metrics
  111. - **[API Reference](https://volcano.dev/docs/api)** - Complete API documentation
  112. - **[Examples](https://volcano.dev/docs/examples)** - Ready-to-run code examples
  113. ## Contributing
  114. We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
  115. ### Questions or Feature Requests?
  116. - πŸ“ [Report bugs or issues](https://github.com/Kong/volcano-agent-sdk/issues)
  117. - πŸ’‘ [Request features or ask questions](https://github.com/Kong/volcano-agent-sdk/discussions)
  118. - ⭐ [Star the project](https://github.com/Kong/volcano-agent-sdk) if you find it useful
  119. ## License
  120. Apache 2.0 - see [LICENSE](LICENSE) file for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.