Clauday.

max-sixty/worktrunk is a CLI for managing git worktrees, built for parallel AI agent workflows. It's at 7,198 stars, it trended again on GitHub with 137 stars in a day, and it ship…

A benchmark called Real-SWE went up at https://withspecific.com/real-swe and the headline number is going to annoy a lot of people: the best model on the board resolves 38.8 percen…

Everyone has the feeling that agent-written code rots faster. Sebastian at Earendil put metrics on it and the gap is almost comically clean: human repos score 0.15 verbosity and 0.…

RTK has been going around as the free lunch of coding agents: pipe your terminal output through it, get 60 to 90 percent token savings. Quesma ran 1,740 benchmark attempts to check…

PI-Desktop jumped 636 stars in a day to 2,250, which for an Electron app with a Rust core is a lot of people quietly agreeing with its premise. The premise: your coding agent shoul…

Cognition shipped SWE-2 on September 10, and the number everyone will quote is 92.8 on Terminal-Bench 2.1, up from 81.5 for SWE-1.7. The number that actually matters is buried one …

openai/plugins gained 505 stars yesterday and sits at 6,161, which is a strange trajectory for a repo that mostly contains JSON. What it holds is the format Codex plugins ship in, …

teamai-cli picked up 563 stars in a day and its pitch fits the problem most teams hit around the third month of agent adoption. Everyone on the team uses a different agent. Claude …

Mastra, the team that came out of Gatsby and went through Y Combinator, launched Mastra Factory as Product Hunt's number one yesterday with 405 upvotes. It is an open-source, agent…

The top organic story on Hacker News yesterday was not a launch or a paper. It was a browser game by a developer named Milos where the whole premise is one sentence: make the Add t…