I needed to put our Anthropic and OpenAI spend next to our cloud bills, and found that the exports don't fit together. The Claude Console gives you two CSVs. The Cost export has dollars rounded to the cent, so a day of cache reads shows $0.00. The Usage export has token counts and no dollars. Anthropic also counts input in four parts that don't overlap: uncached, cache reads, 5-minute cache writes and 1-hour cache writes, priced at 1×, 0.1×, 1.25× and 2× input. OpenAI does it differently: input_
I decided to test this claim with my app, NoMoreHappyPath (NMHP), against Claude on a real project. Here is the test: I built Acremuse, a commercial real estate analysis platform, with Claude Desktop and Codex as a reviewer. It is deployed and used today by a couple of investors. Then I wondered what I'd missed that might bite me later. ~ 374,000 Lines of program code - 1,070 Source files (Python and TypeScript) - ~ 11,400 Functions and methods - 3,067 Automated tests So I gave the same 374k-lin
If you're building an AI agent that buys things for its users, opencommerce by Agentcard gives it one buy tool: search, cart, checkout and order tracking across 5,000+ online stores, through a single endpoint. No merchant integrations to build and no agent browser to run. Agentcard places the order once the user approves. It's fast: it searches catalogues and makes a purchase in under 20 seconds. We test the purchase flow at each monitored store, from search to checkout, and the results are publ
I listed a live agent on the Theagora marketplace (https://theagoralabs.ai) under the name earn-one-dollar. What it is: an agent API that sells an ERC-8004 agent-registry adoption research report. The functionId is earn1usd-erc8004-research. Price is $1.00 (100 USD cents). It auto-executes when bought. How to buy, if you have a Theagora API key: 1. Register an agent on https://theagoralabs.ai (docs: https://theagoralabs.ai/docs). 2. Create an escrow, or place a BID, for functionId earn1usd-erc80
Hey HN, I'm Fabio, the creator of Beolis. I've built Beolis ( https://beolis.com ) to better handle coding on agentic scenarios. It can be used to manage coding with agents in parallel / in the background either in your local machine (using your current repository or git worktrees) or remotely (where it creates a git worktree remotely and works with the agent there). Although it uses agents you don't need to "chat" with the agent at each step as you usually do when dealing with agents
At TechCrunch Founder Summit 2026, happening November 4 at SoWa Power Station in Boston, networking powered by Braindate is designed to make those conversations easier to find, whether they are in 1:1 or small-group on-site meetings. Register before the event starts to save up to $100 on your pass, plus get a second for free.
Runware is building a factory to turn out prefabricated AI data centers on an assembly line. The real test will be whether it can deliver at that scale.
Writing good specs is hard. You don’t know everything upfront and it’s impossible to write every little detail in the spec. Much of my job as a developer has been to treat specs as intent, and fill out the blanks in the code and use the code reviews as a way to question those decisions. But as coding agents have started to produce much more code, the decisions that actually affect the product are getting harder to find. So I created SpecDeck. It helps everyone on the team write specs and hand th