
Billing Infrastructure for AI Startups | Autumn
Billing infrastructure for AI startups, handling payments, usage limits, and credits.
@coleywoleyyy · X
Yup, it’s buns. I vibe coded my own tool at Helicone, might make it easier
The full gallery
Tech stack
25 projects

Billing infrastructure for AI startups, handling payments, usage limits, and credits.
@coleywoleyyy · X
Yup, it’s buns. I vibe coded my own tool at Helicone, might make it easier

Backend infrastructure that keeps AI agents alive with durable execution and state management.
iacguy · HN
Show HN: Durable AI agents without the workflow engine

Monitor LLM calls, APIs, and infrastructure performance for AI agents.
kirankgollu · HN
Oodle.ai – $10 per million agent traces

Platform to run and monitor coding agents continuously from the browser.
sakuraiben · HN
Reachpad – Run all your coding agents from anywhere from the browser

Organize your tools, workflows, and resources into one accessible workspace.
@mj_jimmi · X

Real-time investment terminal that traces global events to their impact on sectors, stocks, and assets.
@codedolphin2 · X

Track AI usage, apply guardrails, and maintain audit evidence for your projects.
@Lathithaa_Mdayi · X

Manage equipment rentals, payments, and inventory tracking in one system.
@ShakibMd93031 · X
Built an Equipment Rental Management System to simplify rentals, payments, and equipment tracking. Looking for businesses interested in a demo or a customized solution.

Build personalized learning paths and track progress in your developer career.
@dipanshurdev

Route your LLM API requests across multiple providers to cut costs and meet latency targets.
Aperswal · HN
Made a Free LLM Router

Optimize electricity spending by connecting utilities, EVs, and solar to find ideal charging times.
@gleam_energy · X
Gleam — an energy management tool that helps people understand, optimize, and save on electricity. Utility data, EVs, solar, batteries, and weather combine to answer questions like "Why did my bill go up?" or "Would switching rate plans save money?"

Check which network routes and Cloudflare nodes various AI services use.
@0xdeusyu · X
想知道代理是不是真的把每个 AI 站都送到同一个出口? 答案:并不是。 我做了一个 AI 分流测试: 它会探测 ChatGPT、Sora、OpenAI、Claude、Grok、Anthropic、Perplexity 等 AI 服务,通过读取各站点的 Cloudflare Edge Trace 信息,获取实际访问情况: 出口 IP Cloudflare 边缘节点(colo) HTTP / TLS / WARP 状态 访问延迟 然后根据落地位置进行归组。 这次测试结果: 6 个服务(覆盖 7 个域名)走美国出口。 唯一例外是 Sora,落在东京节点。 也就是说,同一个代理配置下,不同 AI 服务并不一定经过同一个出口。看起来“都能访问”,实际线路、节点和落地点可能完全不同。 整个测试工具纯前端实现,零后端。