Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.
| Date | Stars |
|---|---|
| 2026-07-31 | 400 |
| 2026-08-06 | 400 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[](https://github.com/Kong/volcano-agent-sdk/actions/workflows/ci.yml)
[](LICENSE)
[](https://www.npmjs.com/package/@volcano.dev/agent)
# 🌋 Volcano Agent SDK
**The TypeScript SDK for Multi-Provider AI Agents**
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 →](https://volcano.dev/)**
## ✨ Features
<table>
<tr>
<td width="33%">
### 🤖 Automatic Tool Selection
LLM automatically picks which MCP tools to call based on your prompt. No manual routing needed.
</td>
<td width="33%">
### 🧩 Multi-Agent Crews
Define specialized agents and let the coordinator autonomously delegate tasks. Like automatic tool selection, but for agents.
</td>
<td width="33%">
### 💬 Conversational Results
Ask questions about what your agent did. Use `.summary()` or `.ask()` instead of parsing JSON.
</td>
</tr>
<tr>
<td width="33%">
### 🔧 100s of Models
OpenAI, Anthropic, Mistral, Bedrock, Vertex, Azure. Switch providers per-step or globally.
</td>
<td width="33%">
### 🔄 Advanced Patterns
Parallel execution, branching, loops, sub-agent composition. Enterprise-grade workflow control.
</td>
<td width="33%">
### 📡 Streaming
Stream tokens in real-time as LLMs generate them. Perfect for chat UIs and SSE endpoints.
</td>
</tr>
<tr>
<td width="33%">
### 🛡️ TypeScript-First
Full type safety with IntelliSense. Catch errors before runtime.
</td>
<td width="33%">
### 📊 Observability
OpenTelemetry traces and metrics. Export to Jaeger, Prometheus, DataDog, or any OTLP backend.
</td>
<td width="33%">
### ⚡ Production-Ready
Built-in retries, timeouts, error handling, and connection pooling. Battle-tested at scale.
</td>
</tr>
</table>
**[Explore all features →](https://volcano.dev/docs#key-features)**
## Quick Start
### Installation
```bash
npm install @volcano.dev/agent
```
That's it! Includes MCP support and all common LLM providers (OpenAI, Anthropic, Mistral, Llama, Vertex).
**[View installation guide →](https://volcano.dev/docs#installation)**
### Hello World with Automatic Tool Selection
```ts
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
```ts
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 →](https://volcano.dev/docs/examples)**
## Documentation
### 📖 Comprehensive GuidesExcerpt of 5,283 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:76400c9221aa83fc, topic:agents, topic:agentic, topic:agentic-ai
matched fp:76400c9221aa83fc, topic:mcp, topic:mcp-server, topic:mcp-client