
SuperCompress - Cut Your LLM Token Costs by 65%
开源提示词压缩,在API调用前压缩输入以降低LLM成本。
@asgujjuasitgets · X
完整作品展
技术栈
60 projects

开源提示词压缩,在API调用前压缩输入以降低LLM成本。
@asgujjuasitgets · X

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.

对你的网络应用和 API 运行真实漏洞测试,用完整证明展示每个安全发现。
@yedil_bek · X
Building RedRun - security testing that proves what it finds. Runs the real exploit + hands you the exact request/response: SQLi, IDOR, SSRF, XSS, JWT + AI prompt-injection. Zero false positives. Free scan → Active engine invite-only - DM for access code

在统一界面编写、模板化并启动跨多个AI平台的提示词。
@promptboxxx · X
Have all your AIs in one place and never repeat a prompt

在浏览器中直接测试OpenAPI端点、对比规范、生成模拟数据。
@_codewithshahid · X

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.

通过统一 API 层将网站与多个 AI 系统集成。
@rofarkas · X

将CVE漏洞数据转换为机器可读风险信号,供AI代理和自动化系统使用。
robert_marshall5 · Product Hunt
attestd CVE and supply chain risk signals for autonomous AI agents.

通过实时压缩提示词和检测重复工具调用,将AI代理的Token成本降低40-70%。
@DeveloperL92487 · X
I built my first app in 60min And now I got $500 MRR in one month Check here if you are interested It’s a tool to reduce agent token consumption, speed up agent response, and clean up memory cache

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.