OpenCode vs Crush: what 3 developers chose.
806 opinions. 3 developers named a direct preference: Crush 2–1. Approval is 66% vs 77%.
If you want cost & pricing, choose OpenCode. If you want UX, choose Crush. The 2–1 direct split is not a landslide; it is a difference in working style.
Choose OpenCode if you…
- Want the larger evidence base
- Care most about cost and customization
- Can accept weaker reliability reports
Choose Crush if you…
- Want a single Go binary
- Prefer minimal configuration
- Value a higher approval rate on a small sample
Cost & pricing for OpenCode. UX for Crush.
Net sentiment per topic: praise minus complaints, as a share of mentions. Positive means more praise than complaints. Hover a dot for the raw counts.
Net sentiment = praise minus complaints, as a share of each tool's mentions. The dot lanes are only for readability; position is the score.
View data table
| Topic | OpenCode | Crush | Mentions |
|---|---|---|---|
| UX | +34 | +43 | 142 / 7 |
| Customization | +82 | +100 | 91 / 3 |
| Open source | +68 | +33 | 37 / 3 |
The same decision, from both sides.
Paraphrased from comments where a developer named a preference or described a switch. Each links to the original.
Picked OpenCode 1 developers
Switched from Crush to OpenCode because Crush lacked plan mode and subagents and did not appear to be adding them.
Picked Crush 2 developers
Chose Crush because it works better than OpenCode for their work, ships as one Go binary, and is easier to reason about.
Moved to Crush after OpenCode ran out of memory on a 512 MB VPS and Crush provided the simple UI and setup they wanted.
The numbers.
| Metric | OpenCode | Crush |
|---|---|---|
| Approval | 66% | 77% |
| Last 90 days | 55% | – |
| Opinions | 780 | 26 |
| Developers | 569 | 18 |
| First-hand opinions | 597 | 19 |
| Direct picks | 1 | 2 |
| Type | Terminal agent | Terminal agent |
| Made by | Open source | Charm |
| Website | Visit ↗ | Visit ↗ |
Related matchups.
Claude Code vs OpenCode
73–42 direct picks, and a clear difference in what developers optimise for.
OpenCode vs Pi
35–11 direct picks, and a clear difference in what developers optimise for.
OpenAI Codex vs OpenCode
14–7 direct picks, and a clear difference in what developers optimise for.
How to read this comparison.
Approval is the positive share of opinions that took a side, with the rank based on the lower bound of a 90% confidence interval. Direct picks count comments where a developer explicitly preferred one tool or described switching. Small samples are noisier; check the opinion counts.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.