Tim O’Reilly built a publishing empire that AI is helping to destroy. Yet he loves AI—as long as it’s open source.
Hey HN!We all know that most public evals are saturated and are hard to trust. What matters is whether a model reliably works in your codebase in your actual day-to-day-work.To solve this, we built self-bench (https://github.com/mupt-ai/self-bench), an open-s…
Meta-harness that runs Claude Code and Codex CLI with live trace sync.
Agent Unit Economics SDK — track end-to-end business-task costs for AI agents.
Article URL: https://github.com/vercel-labs/eve-software-factory-template Comments URL: https://news.ycombinator.com/item?id=49300390 Points: 2 # Comments: 0
