The step up from there is an editor with a built-in agent like Cursor, Google Antigravity, Windsurf, or VS Code with a coding extension. These are code editors with an AI agent living inside them, and the difference is the responsible party for getting things from place to place. Instead of the software creator shuttling code between windows, the AI agent edits the project files directly and runs the GitHub and... - Source: dev.to / 8 days ago

If you were similarly flashbanged by the Antigravity 2.0 update, here is a complete breakdown of what Google changed, the data behind the new features, why it broke our setups, and the exact steps I used to repair my workspace. - Source: dev.to / 14 days ago

Welcome back to The Agent Factory! This week, we went beyond the hype to dissect the technical details of Google's massive wave of AI releases. We were joined by Paige Bailey, the UTL for Developer Relations at DeepMind, to break down everything from the new Gemini 3 model to the Antigravity IDE. - Source: dev.to / 4 months ago

I thought most people used Antigravity to code with Gemini? https://antigravity.google/. - Source: Hacker News / about 1 month ago

Two interesting ones I've been playing with, JetBrains Air and Google Antigravity. Google recently used Antigravity 2.0 to build a custom OS and run Doom during their I/O 2026 keynote, so I'm really interested to see where this goes. Will report back after a few months. - Source: dev.to / about 1 month ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / about 16 hours ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 4 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 5 days ago

Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 13 days ago

If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 14 days ago