
Omna — The universal semantic layer between your data and AI
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
完整作品展
技术栈
22 projects

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

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

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。

GoldBean: 按次付费API市场,拥有47个AI接口(OCR、翻译、图像生成、LLM聊天等)。
13639366668 · HN
Pay-per-call MCP server with 47 AI endpoints, micropayments via x402


通过IPClues快速查询IP地址的国家、ASN和组织信息。
@IPClues · X
Hey, developers and SaaS founders, this is newly hatching Internet Intelligence. is an IP-to-Geolocation service for you head over and test before it is released to public.

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.

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

根据硬件规格发现本地可运行的AI模型,包括性能和价格估算。
cdnsteve · HN
Tokenstead, find AI models for your hardware

免费阅读财务电话会议记录,或通过 REST API 和 MCP server 访问
@RobGuerra90 · X
Building : access earnings call transcripts via a cheap API or MCP server. Pull any company's call right into your workflow.