Claude Code vs Kiro: what 6 developers chose.
3,064 opinions. 6 developers named a direct preference: tied. Approval is 54% vs 59%.
If you want autonomy, choose Claude Code. If you want UX, choose Kiro. The 3–3 direct split is not a landslide; it is a difference in working style.
Choose Claude Code if you…
- Want the larger evidence base: 3,026 opinions from 2,204 authors
- Care about autonomy and code quality, net +192 and +51
- Can tolerate reliability and usage-limit complaints, net -189 and -100
Choose Kiro if you…
- Prefer a simpler IDE-style UX, 8 positive to 3 negative
- Want a cheaper entry point: 3 positive cost mentions to 1 negative, on a $20 plan
- Work where Kiro is supplied, such as Amazon, and want its CLI or spec generator
Autonomy for Claude Code. UX for Kiro.
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 | Claude Code | Kiro | Mentions |
|---|---|---|---|
| Autonomy | +52 | +100 | 368 / 4 |
| UX | -3 | +45 | 437 / 11 |
| Code quality | +12 | -20 | 429 / 5 |
| Reliability | -47 | -33 | 403 / 6 |
| Cost & pricing | -18 | +50 | 313 / 4 |
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 Claude Code 3 developers
Kiro is second to Claude Code and that Amazon's real target is only beating Copilot.
Kiro may have a first-mover advantage inside Amazon, but Claude Code feels better to use.
Amazon engineer says most gripes are with Kiro's harness and Claude Code is much better, citing 2-4x productivity at work.
Picked Kiro 3 developers
Amazon employee here. - Can confirm that channel exists and it's great. Rofl every day for all the stupidity happening in the company. - Despite many seeing Amazon as outsider for AI, it's actually a great place to work (if not fired). We have free access to all frontier models, including today's Mythos release for all employees. - Every model available on Bedrock is available for free with no caps. I think it's because these models are deployed on trainium chips which is essentially free for Amazon. - Claude code and Codex are available unlimited for employees. - For this one I will be bitten
I feel Gastown is an attempt at answering: what if i push the multi-agent paradigm to its chaotic end? But I think the point that Yegge doesn't address and that I had to discover for myself is: getting many agents working in parallel doing different things -- while cool and exciting (in an anthromorphic way) -- might not actually be solving the right problem. The bottleneck in development isn't workflow orchestration (what Gastown does) -- it's actually problem decomposition . And Beads doesn't actually handle the decomposed problem well. I thought it did. But all it is is a task-graph system.
Result quality is similar, but Claude Code got stuck on tool-call errors while Kiro worked, and Kiro's UX is simpler.
The numbers.
| Metric | Claude Code | Kiro |
|---|---|---|
| Approval | 54% | 59% |
| Last 90 days | 51% | – |
| Opinions | 3,026 | 38 |
| Developers | 2,204 | 30 |
| First-hand opinions | 2,397 | 26 |
| Direct picks | 3 | 3 |
| Type | Terminal agent | AI IDE |
| Made by | Anthropic | AWS |
| Website | Visit ↗ | Visit ↗ |
Related matchups.
Claude Code vs OpenAI Codex
181–62 direct picks, and a clear difference in what developers optimise for.
Claude Code vs OpenCode
73–42 direct picks, and a clear difference in what developers optimise for.
Claude Code vs Cursor
61–42 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.