Agents-Flex 记录了 5,088 月访问量，月度环比增长为 +202.3%，定价为 Free / Open Source。Agentset 记录了 6,469 月访问量，增长率为 -29.3%，定价为免费增值，定价请咨询。
开源 Java 框架，用于构建 AI 智能体与 LLM 应用
面向可靠 AI 对话与搜索的开源 RAG 平台
| 维度 / 指标 | | |
|---|---|---|
| 官方域名 | agentsflex.com | agentset.ai |
| 定价模式 | Free / Open Source | 免费增值，定价请咨询 |
| 月访问量 | 5088 (5,088) | 6469 (6,469) |
| 月度环比流量变化 | +3405 (+202.3%) | -2682 (-29.3%) |
| 主要市场与份额 | 🇨🇳 中国 (100%) | 🇺🇸 美国 (33.6%) |
| 直接访问 / 月 | 426 | 2569 |
| 用户评分 | 4.6 | 4.6 |
| 支持的平台 | 网站 | 网站 |
开源 Java 框架，用于构建 AI 智能体与 LLM 应用
为任意受支持的提供商配置 API Key 与模型名，再通过 chat() 调用，获得跨模型一致的接口体验。
AgentRunner 结合策略与中间件，在单一执行流中协调模型、工具与沙箱。
可复用、可版本化的能力定义，捆绑 SKILL.md、脚本与资源，可从本地目录或远程存储发现并加载。
按需加入知识检索、图像生成与 OCR 流程，灵活混合同步与异步执行方式。
面向可靠 AI 对话与搜索的开源 RAG 平台
结合智能体推理、混合检索与重排序，即使面对庞大杂乱的文档集也能给出准确答案。
每条答案都附带来源段落引用，用户可随时核查答案出处。
不仅能索引文本，还能处理图片、图表、表格，并通过 SDK 支持 PDF、DOCX、XLSX、PPTX、HTML、EML 等 22 种以上格式。
可接入自有 LLM、嵌入模型与向量数据库，包括 OpenAI、Anthropic、Google、Cohere、Pinecone、Qdrant 等。
免费 / 开源在本地或云端运行和构建开源 AI 模型
让 AI 智能体安全接入 1700+ 应用
免费 / 开源Mastra is an open-source TypeScript framework for building, deploying, and observing AI agents and workflows. It gives JavaScript developers typed agents, durable workflows, memory, MCP tool support, and built-in observability so prototypes can scale into production.
免费 / 开源Mastra is an open-source TypeScript framework for building, deploying, and observing AI agents and workflows. It gives JavaScript developers typed agents, durable workflows, memory, MCP tool support, and built-in observability so prototypes can scale into production.
专项更强Pinecone is a managed vector database and AI knowledge platform for building retrieval-augmented generation (RAG), semantic search, and agent memory. It stores vector embeddings at scale, makes writes searchable within seconds with no index tuning, and keeps p99 latency steady as data grows. Pinecone powers products for more than 10,000 customers and over a million developers worldwide.
专项更强Pinecone is a managed vector database and AI knowledge platform for building retrieval-augmented generation (RAG), semantic search, and agent memory. It stores vector embeddings at scale, makes writes searchable within seconds with no index tuning, and keeps p99 latency steady as data grows. Pinecone powers products for more than 10,000 customers and over a million developers worldwide.
免费 / 开源Qdrant is an open-source vector search engine and database, written in Rust, for high-performance similarity search in AI applications.
面向编程智能体的智能模型路由
