AllyshipContent Radar

Hands-on 193

Công cụ, thử nghiệm và hướng dẫn thực hành

Crawl live-1795068900000 · 13:22 19 thg 11, 2026 · Xuất bản 13:29 19 thg 11, 2026

1

Launch HN: Pomerado (YC F26) – Turn any website into an MCP for agents

72.5

Hướng dẫn alanjm23

Hi HN, we’re Alan and Akshay from Pomerado ( https://pomerado.ai/ ). We connect your agents to any website by turning sites into deterministic, self-healing APIs in minutes, fully self-serve. Agents are no longer limited by their intelligence, but rather by their ability to interact with systems. Airlines, banks, e-commerce, insurance portals, government sites, and legacy portals all lack APIs or MCPs and are common parts of personal assistant or business workflows. Agents instead rely on browser automation or computer use, which can be slow, expensive, and unreliable. And even if computer use were perfect, most companies have banned it out of security and compliance concerns. We discovered this problem while tinkering with our own personal assistants. When OpenClaw came out, we wanted to “live our lives through our agents” and have them do everything for us. We soon found their usefulness was restricted by what tools they could connect to. For example, when trying to book flights, they fell back on computer use, which failed to checkout. These issues got magnified on repeated workflows, like searching many airlines at once. Pomerado started off as a project to improve these personal assistant workflows. As we started building, we realized that just-in-time tool creation could have significant applications for AI builders in legacy verticals. We’re ex-McKinsey and Scale AI, where we drove agent deployments in healthcare, professional services, and telecom. Each time, the biggest bottleneck was getting agents to interface well with legacy websites and apps. Pomerado is what we built. It’s a self-serve platform where devs can create APIs for any website (even those they don’t own), in minutes. Users (or their coding agents) provide a short natural language description, answer a few questions about their workflow, and receive a MCP in less than an hour. Future tool calls use the deterministic MCP, which usually returns results in 5-30 seconds. Here’s a walkthrough of our product: https://youtu.be/Bi4jci7rgHo In practice: - Our agent opens a browser, explores the website, and performs the requested task once by writing HTTP requests or a Playwright script. This example run establishes how to navigate the website, interact with the relevant controls, and obtain the desired result. If any additional user input is needed (e.g., login, clarification) the agent will ask the user over MCP. - Afterwards, the agent uses the example run, along with all of the data it recorded, to create a generalizable and repeatable API. Throughout this process, a separate Guardian model reviews the coding agent’s calls against a set of guardrails. We also run a battery of tests with synthetic inputs to ensure that the API is generalized and not overfit to one input. A final publication agent ensures that the integration publishes a reasonable and generalized input/output schema - We also handle sites that require authentication and 2FA. For authentication, we pass off to a deterministic sign-in process to ensure the model and our recorders never read customer credentials. Users can store 2FA TOTP seeds or link their account to a Pomerado phone number for us to autofill 2FA for them as well - If future runs fail, a maintenance job is kicked off to repair and improve the tool. The maintenance job can fix broken steps (e.g., a renamed button), add additional functionality (e.g., searching for business class flights in addition to economy), or add new guardrails (e.g., reservation dates must be in the future). We’ve even seen people improve tools by just saying “please make this faster” Unlike computer use, our MCPs are deterministic at runtime, which makes them much faster and cheaper. By taking slightly longer to do a task the first time, you reap the benefits much more in the future. It’s a great fit for repeated, high-volume tasks you want your agent to do. We’d love to have you try it! We have both an open-source (MIT) ( https://github.com/Pomerado/pomerado ) and a free hosted version ( https://app.pomerado.ai ). So far, users of Pomerado include: - A personal trainer using agents to prepare workouts and message clients. Before Pomerado, agents couldn’t login and use the site reliably, so this was all manual - Car dealerships connecting their Grok Bots to legacy dealer systems, including marketplaces, CRMs, and ERPs. Dealers switched from computer use, which could take 1hr+ - Personal assistants using Pomerado to integrate with a broad range of consumer websites Please ask any questions or share any feedback in the comments, thanks!

HN: open weights · 12 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
2

Show HN: A deterministic typesetting tool for Orthodox Music

71.1

Hướng dẫn rpmisms

Tác giả là nhạc sĩ nhà thờ Chính Thống Nga và nhà phát triển phần mềm. Họ nói mình muốn biến Claude Pro subscription thành một động cơ typesetting tất định cho nhạc nhà thờ vốn thường được hát chỉ dựa vào text. Bài đăng nêu rằng không sử dụng AI để xử lý các văn bản; thay vào đó hoàn toàn theo thuật toán.

HN: Claude · 19 thg 11, 2026

Biên tập tiếng Việt
Chi tiết nguồn

I'm a trained Russian Orthodox church musician and software developer. I figured I would flog my Claude Pro subscription into helping me create a deterministic engine for typesetting church music that would otherwise be sung off of text alone in most cases. No AI is used in processing any of the texts, it's entirely algorithmic. Even if you don't have a use case for this, I figured the music nerds out there might appreciate taking a look at it and even perhaps giving a suggestion on how to improve it.

  • No AI is used in processing any of the texts, it's entirely algorithmic.
  • No AI is used in processing any of the texts, it's entirely algorithmic.
3

Show HN: Director's Lookbook, named looks for image, video and music prompts

69.0

Hướng dẫn RiverRoadLabs

Bài đăng giới thiệu Director's Lookbook, một công cụ giúp người dùng gõ một “cảm giác” (feeling) để nhận một bộ thẻ style kèm prompt text để sử dụng, nhằm tránh việc phải copy hay lưu prompt. “Feeling reader” là một mô hình được host với hạn mức allowance miễn phí mỗi ngày. Họ dùng MCP server ở chế độ read only, không auth, không key; connector hoạt động như một kết nối cho Claude và cũng cho Cursor. Công cụ miễn phí, không đăng nhập/tài khoản.

HN: Claude · 18 thg 11, 2026

Biên tập tiếng Việt
Chi tiết nguồn

River Road Labs is a small artisanal studio based out of Central NJ. We built this tool to scratch our own itch. As AI video and image capabilities get more sophisticated we found that we struggled at times to find the words to describe the aesthetic style we were shooting (no pun) for. Other times it is good to just have a massive resource of styles and imagery to flip through at random and to let serendipity do the rest. Director's Lookbook lets you type a feeling and get dealt a set of style cards with prompt text to use. No more copying or saving prompts, use the tool. The feeling reader is a small hosted model with a free daily allowance. The MCP server is read only, no auth, no key, it works in Claude as a connector and in Cursor as well. Setup is at directorslookbook.app/mcp. The connector keeps no request text, only daily counts of which tools were called. The tool is free, no login, no account. We welcome feedback on how to make the tool better and what looks are missing! Thanks!

  • Director's Lookbook lets you type a feeling and get dealt a set of style cards with prompt text to use.
  • Director's Lookbook lets you type a feeling and get dealt a set of style cards with prompt text to use.
  • The MCP server is read only, no auth, no key, it works in Claude as a connector and in Cursor as well.
  • The tool is free, no login, no account.
4

ALIVE: Making Streaming Video Models Interactive

68.3

Hướng dẫn Jinzhao Li, Yuan Xu, Jinxuan Wu, Yukun Wang, Yijia Lei, Hanyu Ji, Yinuo Chen, Zining Huang, Chi Zhang, Hang Ye, Yiwu Zhong, Honglei Yan, Panwang Pan, Yizhou Wang, Yin Li, Miao Liu

Streaming video LLMs can continuously observe the world, yet often handle user requests in isolation. We introduce ALIVE, an interactive streaming video model supporting proactive monitoring, streaming task coordination, and feedback-seeking interaction. We construct ALIVE-SFT-288K and ALIVE-RL-3K for two-stage training. Contrastive supervised fine-tuning teaches when and how to respond, while reinforcement learning with Behavior-Aligned Credit Assignment (BACA) combines trajectory-level and local advantages to refine decisions, responses, and silence across multi-turn interactions. We also introduce FSI-Bench to evaluate feedback seeking and subsequent task completion. ALIVE achieves the highest overall scores among the compared models on four public benchmarks and FSI-Bench, demonstrating strong streaming understanding and interactive capabilities.

Hugging Face Papers · 16 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
5

Show HN: Faros Desktop, a local app to see your AI traces and extend your usage

68.2

Hướng dẫn sachinag

Bài đăng giới thiệu Faros Desktop là app cho Mac trực quan hóa cách người dùng dùng các công cụ AI mã hóa cục bộ, tập trung dữ liệu từ nhiều công cụ để xem và phân tích dấu vết phiên, đồng thời đưa ra khuyến nghị để tối ưu chi phí gói thuê bao. Ứng dụng miễn phí, không cần đăng nhập hay API keys, chỉ dùng mô hình chạy trên thiết bị để tóm tắt lịch sử phiên theo từng đoạn và tổ chức theo dự án/công việc.

HN: AI agent · 18 thg 11, 2026

Biên tập tiếng Việt
Chi tiết nguồn

Hi HN, I’m Sachin, and I’ve spent the last couple of months working on Faros Desktop, a Mac app that visualizes how you use your local AI coding tools into one place and then makes recommendations to make your subscription spend go further. As agents have replaced hands-on-keyboard work, the team and I wanted to better understand what’s in our session traces. Faros Desktop hydrates with on-device session history in Codex, Claude Code, Github Copilot, and Cursor to let users deep dive into a beautiful visualization of AI session traces. Then based on consolidating that information, the app shows patterns in usage as well as recommendations for ways to save spend through simple changes that we call Power Ups. Faros Desktop is totally free, with no login required and no API keys needed. The app also only uses on-device models to summarize local sessions in chunks, then organizes them by project and task. You can jump around a session timeline and see exactly the messages and tool calls in the trace. The business model here for Faros Desktop is to drive thought leadership and create leads for our sales team to sell the company’s multi-player Token Engineering Platform for large engineering organizations. Faros has been serving large engineering organizations for the past seven years, so it was cool to be able to build a product for all Builders, not just enterprise engineering orgs. One big direction we’re exploring: using previous sessions to make the next one better. We’re looking at local memory portability across harnesses as well as multi-player modes to share memory within your direct team. I’d love to hear thoughts on that. Docs and product walkthrough: https://docs.desktop.faros.ai/ Setup: https://docs.desktop.faros.ai/getting-started/install-and-se... Data handling: https://docs.desktop.faros.ai/settings-and-privacy/understan... Faros website: https://www.faros.ai/

  • Faros Desktop hydrates with on-device session history in Codex, Claude Code, Github Copilot, and Cursor
  • Faros Desktop hydrates with on-device session history in Codex, Claude Code, Github Copilot, and Cursor
  • Faros Desktop is totally free, with no login required and no API keys needed.
  • The app also only uses on-device models to summarize local sessions in chunks, then organizes them by project and task.
6

Show HN: Tool to measure log TCO savings without losing or migrating any data

66.3

Hướng dẫn rinkash

Bài đăng giới thiệu Chiron, cung cấp giải pháp “lossless consolidation” để tiết kiệm chi phí log trên các hệ lưu trữ chất lượng cao như Splunk mà không làm mất dữ liệu, kết quả truy vấn vẫn giữ nguyên và vẫn đáp ứng yêu cầu compliance. Họ xây dựng một estimator tool dạng binary để người dùng tự ước tính mức tiết kiệm trên dữ liệu log của mình trước khi liên hệ; tool có MCP server và một skill, được dùng với Claude/Cursor để xử lý từ folder local, không để dữ liệu rời khỏi mạng và không gửi dữ liệu tới model (chỉ gửi tóm tắt thống kê và metadata).

HN: Claude · 18 thg 11, 2026

Biên tập tiếng Việt
Chi tiết nguồn

I work on Chiron. We provide a “lossless consolidation” solution for log savings on high-fidelity stores like Splunk, where you don’t lose any data, your query results stay intact, and you still meet your compliance needs. On a Palo Alto firewall log sample we published, the lossless merge came to about 40%. Method and numbers: https://medium.com/@chironvision_inc/keeping-palo-alto-logs-... We built this estimator tool so that people can get a savings number on their own logs before they reach out to us. It is a binary tool with an MCP server plus a skill. Point your Claude, Cursor or similar at a local folder where your log sample is located. The tool produces a savings estimate report. It makes sure that no data leaves your network, and no data goes to your model either. The model only gets a statistical summary and metadata. Install (or grab the tarball from the same path; checksums.txt is there, and releases are Sigstore signed): curl -fsSL https://www.chironvision.com/dl/ea324478d02311d6b42f939c08b0... | bash -s -- --target claude The tool comes with a zookeeper sample bundled so you can quickly test and validate the setup. Currently supported log formats: Splunk exports, OTLP JSON, k8s container logs, plain text. The detailed README on how to use the tool is included in the download. How the tool works: it reads the logs from the provided folder or files and runs the analyzer to compute the lossless savings. The tool interacts via the MCP server with your Claude console or similar. You can run it from your Claude or Cursor console. The engine is a binary, not open source; the license is at the download path. Run the sample, then a few minutes of your own logs

  • The tool produces a savings estimate report.
  • The tool produces a savings estimate report.
  • It makes sure that no data leaves your network, and no data goes to your model either. The model only gets a statistical summary and metadata.
  • It is a binary tool with an MCP server plus a skill. Point your Claude, Cursor or similar at a local folder where your log sample is located.
1–6 / 106
Trang 1 / 18