I’ve been building OxCode with a very determined team: an AI software engineer that runs inside VS Code and editors that use Open VSX. It plans, writes, tests and debugs code. On a single attempt it scores 82% on SWE-bench Verified (410/500) and 73/89 on Terminal-Bench 2.1. The full results and the eval setup are public at Benchmarks | OxCode. I’d love feedback from people who work on coding agents: where does it fail on your real repos, which tasks should we add to the evals, and what would make you trust an agent’s patch? It’s free to start: OxCode - AI Software Engineer - Visual Studio Marketplace. Replies here are welcome.
Add Local Developer Utilities to Any MCP Assistant with DevUtils