OpenAI Codex vs Kilo Code: what developers actually say
Based on 2,044 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
OpenAI Codex comes out ahead overall on volume, approval, code quality, cost sentiment, and autonomy. It has 2,013 opinions from 1,386 authors and 69% approval, versus 31 opinions and 63% for Kilo Code. Codex scores 343 positive to 116 negative on code quality, 174 to 54 on cost/pricing, and 169 to 46 on autonomy, while reliability is its weak spot at 112 positive to 127 negative. Kilo Code is the better pick for an open-source VS Code extension with provider switching and customization; its small sample shows 4 positive and 0 negative on customization.
When developers explicitly said they prefer one or switched: 0 picked OpenAI Codex, 1 picked Kilo Code.
Choose OpenAI Codex if
- Want a terminal agent with broad HN coverage
- Value strong code-quality and autonomy signals
- Can accept reliability complaints and usage limits
Choose Kilo Code if
- Want an open-source IDE extension
- Want to switch providers mid-task
- Prefer a VS Code plugin over a terminal workflow
Where each one wins and loses
Why developers switched
Picked OpenAI Codex
No explicit switches recorded.
Picked Kilo Code
Summaries are paraphrased. Each links to the original comment.