完整作品展
技术栈
31 projects
通过 SDK、CLI、MCP 等方式将 1000+ SaaS 应用连接到 AI 代理。
oomol-lab · GitHub
open-connector Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
免费的本地优先 API 客户端，支持 HTTP、WebSocket、GraphQL、gRPC、MQTT 等。无需账户或云端。
@HalxDocs · X
Reqit—a fast, local-first API client for developers.
为自由职业者打造的客户门户，在一个地方收集客户简介、文件和反馈。
@DropKlient · X
The only website freelancers need to manage their work.
RequestHarbor 安全客户门户，用于共享文件、答案和批准，实时可见状态。
@danielkleach · X
is a branded client portal for files, answers, sign-offs, and signatures. No more scattered email threads, docs in Google Drive, or confusion about who is waiting for whom. Business and client both see what is done and what is in progress on both sides, in
用可视化编辑器设计、测试和发布AI就绪的API。
@milonspace · X
A specification nobody can find is functionally the same as no specification.
在本地处理数据以隐藏个人信息并降低向 Claude、ChatGPT、Gemini 等 API 发送数据的 token 成本。
@AI_303030 · X
将 OpenAPI 规范和数据库转换为 MCP 工具，无需编码。
mhmt_dmr · HN
MCP Gateway – Turn existing APIs and databases into MCP servers
统一API网关，审计Token消耗并分析多个AI提供商的成本。
@amiuchat · X
我做了一个桌面工具：Token Switch。 给 Codex / Claude Code / OpenCode 重度用户统一管理 Provider、模型、Token、Base URL、连通测试和消耗统计。 多个 Agent，一个 Token 工作台。欢迎试用，也欢迎吐槽你最烦的配置问题。
通过 EmoToken API 网关访问 Claude 模型,包含控制台和集成支持。
hywpinbo · V2EX
[分享] emoToken — 自己做的 Claude API 服务,注册送 $3 最近做了个 Claude API 服务 **emoToken**,分享给有需要的朋友。 官网:https://emotoken.com ## 支持的模型 - Claude Opus 4.8 / 4.7 / 4.6 - Claude Sonnet 4.6 / 4.5 / Sonnet 5 - Claude Haiku 4.5 - Claude Fable 5(最强模型) 接入方式登录后在控制台左侧「接入文档」里有详细教程。 ## 一点福利 - 注册即送 $3 体验额度 - 有问题可以在 Discord 找我们:https://discord.gg/BVeJW7aHj 自己用 Claude 比较多,顺手做成了服务。欢迎试用,有问题直接反馈。
与客户共享文件和讨论文档的门户，无需客户注册。
@droplana_com · X
可嵌入的可视化工作流编辑器，支持AI驱动或纯逻辑设计。
tahazsh · HN
Hi! I’m Taha. In many agentic products that support workflows (including one I worked on), I noticed they either don’t support node-based editors, or use React Flow and go through the difficult work of integrating it into their product to run it and work with their existing logic. So I thought about creating a tool that could help with this by closing the gap between the editor and the runtime. That’s why I created Wayflow. The basic architecture is simple: you just need to create a graph (which is a JSON object) that the runtime knows how to run. The runtime doesn’t care where that graph is coming from, it just needs the right schema. And with the help of the editor, you can create the graph, and then export it or directly save it on your backend in your database. And then when you want to execute it, you just hand it to the runtime. The runtime can either stream the execution (which is useful for the editor), or give you the final result. How you execute the graph is up to you: t
