HackerNews中文版

您好，我一直在使用各种框架构建小型 AI 智能体，有一件事一直困扰我，那就是在提示、流程、工具等小细节上进行迭代时，总是需要更改代码 + 部署应用程序。虽然提示部分可以用 Langfuse 解决，但我还没有找到一种好的方法来远程管理流程（并且是开源的）。最近我一直在使用 Genkit (<a href="https://github.com/firebase/genkit" rel="nofollow">https://github.com/firebase/genkit</a>)，非常喜欢它的模块化。所以我想，为什么不在它之上构建一个 UI 构建器，它可以处理简单的流程、提示和基本的追踪。现在我们有了第一个早期版本：<a href="https://flowshapr.ai" rel="nofollow">https://flowshapr.ai</a> 代码库：<a href="https://github.com/flowshapr/flowshapr" rel="nofollow">https://github.com/flowshapr/flowshapr</a> 此第一个版本可以： - 远程管理和执行简单的流程 - 适用于 GoogleAI、Anthropic 或 OpenAI - 与远程 MCP 工具集成 - 用于远程执行流程的 API 端点 - 流程和流程 URL 与 genkit 客户端 SDK 兼容即将推出： - 对 Ollama 的支持 - 对各种向量数据库的支持 - 更复杂的多智能体流程 - 会话管理欢迎任何反馈和建议！

查看原文

Hi,I have been building small AI Agents for quite some time now using various frameworks and one thing that always bugged me was that iterating on small things like prompts, flows, tools etc always took a code change + deployment of the app. While the prompt part can be solved with Langfuse I haven't found a good way to keep the flow management remote (and open source).Lately I have been working with Genkit (<a href="https://github.com/firebase/genkit" rel="nofollow">https://github.com/firebase/genkit</a>) and love how modular it is. So I thought why not build a UI builder on top of that that can handle simple flows, prompts and basic tracing.And here we are with a first early version: <a href="https://flowshapr.ai" rel="nofollow">https://flowshapr.ai</a> Repo: <a href="https://github.com/flowshapr/flowshapr" rel="nofollow">https://github.com/flowshapr/flowshapr</a>This first release can - Manage and execute simple flows remotely - Works with GoogleAI, Anthropic or OpenAi - Integrate with remote MCP tools - API Endpoint to execute flows remotely - Flows and flow urls are compatible with the genkit client sdkUpcoming - Support for Ollama - Support for various vector stores - More complex multi agent flows - Session managementAny feedback and suggestions are welcome!

Show HN：我构建了一个用于 Genkit AI 流程的开源拖放编辑器