GitHub

volcano-agent-sdk

Agent 框架 MCP 工具

观察池 · 暂无正式排名

该项目当前未满足“两个有效维度 + 两种数据源”的主榜门槛。

— 未排名

可观测采用度缺失

—

动量当前有效 · 2026-09-12

关注度当前有效 · 2026-09-12

信号可信度 依据当前有数据的独立评分维度数量计算。

中2/3 · 1 种数据源

方法论 v2.0 · 快照 2026-09-12 · 超过 2 天视为过期

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…

各数据源

GitHub Kong/volcano-agent-sdk 指标与趋势 →

405 Star

Star 405
Fork 32
提交 65
发布 3