June 13, 2026

neonctl psql used to fail with "command not found" whenever psql wasn't on your PATH — which is most macOS laptops, slim Linux containers, Windows boxes, CI runners, and sandboxes. So we did the uncomfortable thing: reimplemented the psql client in pure TypeScript, embedded it in the CLI, and built a byte-exact conformance harness against PostgreSQL's own regression suite to prove it actually behaves like psql...

## What's Changed * [codex] add BU3 browser use models by @MagMueller in https://github.com/browser-use/browser-use/pull/5002 * [ENG-4762] publish: gate publish_to_pypi behind release env by @LarsenCundric in https://github.com/browser-use/browser-use/pull/5013 * feat(llm): accept provider-prefixed models in ChatBrowserUse by @sauravpanda in https://github.com/browser-use/browser-use/pull/5007 * chore(llm): remove bu-3 / bu-3-max, default beta example to openai/gpt-5.5 by @sauravpanda in https:/

olmo-eval: An evaluation workbench for the model development loop

's native Nitro v3 integration is now in beta. Steps run inside the same bundled runtime as the rest of your app, instead of a separate bundle. Nitro's and other server-side APIs work directly inside functions. Workflow SDK useStorage() "use step" The Nitro dev server also serves the workflow web UI at . Open it in your browser to inspect, monitor, and debug workflow runs. /_workflow Workflow routes are now bundled by Nitro as part of the app build. Dependencies are traced, and unused code is tr

## What's Changed * Fixed `ollama launch` selecting the wrong provider in some cases * Improved prompt caching by decoupling it from context shift for better KV cache reuse * More stable MLX inference with hardened linear and embedding layers * MLX runner now creates snapshots during prompt processing and speculative decoding for improved reliability * Improved recurrent model support with per-boundary states from the gated-delta kernels **Full Changelog**: https://github.com/ollama/ollama/compa

Hey all, I built StackScope, a crawler/catalogue that looks at new product launches and shows what they were built with. It watches launches from Product Hunt, Show HN, and PeerPush, then crawls the public site behind each one. The goal is to show what people actually launched with: hosting, frameworks, analytics, DNS, security headers, legal pages, AI-builder signals, and other public clues. I started building it because most stack-detection sites look at the web as a whole. I was more interest