{"slug": "kiro", "name": "Kiro", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 11, "warners": 0, "score": 4.904, "rising": -0.98, "first": "2026-02-12", "latest": "2026-09-07", "why": "I switched to Kiro and it's essentially identical.. well a bit better because you get a better idea of what the harness is doing", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 9, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I switched to Kiro and it's essentially identical.. well a bit better because you get a better idea of what the harness is doing", "icon": true, "domain": null, "github_repo": null, "official_url": "https://kiro.dev", "pricing": "", "aliases": ["Kiro"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 781022240, "item_id": 48813890, "url": "https://news.ycombinator.com/item?id=48813890", "by": "danny_codes", "date": "2026-07-06", "stance": "recommend", "quote": "I switched to Kiro and it's essentially identical.. well a bit better because you get a better idea of what the harness is doing", "excerpt": "Is it? I switched to Kiro and it's essentially identical.. well a bit better because you get a better idea of what the harness is doing, but otherwise identical.", "context": "", "use_case": "AI coding harness", "switched_from": "", "story": "GLM 5.2 and the coming AI margin collapse"}, {"id": 766837968, "item_id": 47927373, "url": "https://news.ycombinator.com/item?id=47927373", "by": "topce", "date": "2026-04-27", "stance": "recommend", "quote": "IMHO lot of people will switch to kiro and or deep seek", "excerpt": "I used both copilot and kiro copilot sonet 1 copilot opus 3 kiro sonet 1.3 kiro opus 2.2 IMHO lot of people will switch to kiro and or deep seek it look like AWS done best inference google is another big player , has model and also cloud byt my 2 cents form Cents on AWS", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Microsoft to Stop Sharing Revenue with Main AI Partner OpenAI"}, {"id": 753727216, "item_id": 47107951, "url": "https://news.ycombinator.com/item?id=47107951", "by": "achenatx", "date": "2026-02-21", "stance": "recommend", "quote": "I can let it run for an hour or more in this mode. Then there is lots of stuff to fix, but it is mostly correct.", "excerpt": "I use amazon kiro. The AI first works with you to write requirements, then it produces a design, then a task list. The helps the AI to make smaller chunks to work on, it will work on one task at a time. I can let it run for an hour or more in this mode. Then there is lots of stuff to fix, but it is mostly correct. Kiro also supports steering files, they are files that try to lock the AI in for common design decisions", "context": "", "use_case": "spec-driven AI coding", "switched_from": "", "story": "How I use Claude Code: Separation of planning and execution"}]}], "caveats": [], "who": [{"by": "ygjb", "context": "uses skills, SOPs, scripts and MCP servers extensively", "url": "https://news.ycombinator.com/item?id=49594458", "date": "2026-09-07"}, {"by": "mlaretallack", "context": "runs about 4 projects at a time", "url": "https://news.ycombinator.com/item?id=46999385", "date": "2026-02-12"}], "tags": [], "use_cases": ["ai coding", "skills and session analysis", "coding with claude", "agent skill for demo creation", "professional ai coding", "coding agent in a swarm"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 6, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 762608802, "item_id": 47663050, "url": "https://news.ycombinator.com/item?id=47663050", "by": "thrtythreeforty", "date": "2026-04-06", "stance": "compare", "quote": "Amazon's Kiro is \"we have Claude Code at home\" but it still eventually uses Opus as the model", "excerpt": "I noticed this almost immediately when attempting to switch to Opus 4.6. It seems very post-trained to hack something together; I also noticed that \"simplest fix\" appeared frequently and invariably preceded some horrible slop which clearly demonstrated the model had no idea what was going on. The link suggests this is due to lack of research. At Amazon we can switch the model we use since it's all backed by the Bedro", "context": "works at Amazon", "use_case": "coding agent", "switched_from": "", "story": "Claude Code is unusable for complex engineering tasks with the Feb updates"}, {"id": 758278720, "item_id": 47392420, "url": "https://news.ycombinator.com/item?id=47392420", "by": "humbleharbinger", "date": "2026-03-15", "stance": "warn", "quote": "Most of my gripes are with the harness, CC is way better.", "excerpt": "I'm an engineer at Amazon - we use Kiro (our own harness) with Opus 4.6 underneath. Most of my gripes are with the harness, CC is way better. In terms of productivity I'm def 2-4X more productive at work, >10x more productive on my side business. I used to work overtime to deliver my features. Now I work 9-5 and am job hunting on the side while delivering relatively more features. I think a lot of people are missing ", "context": "engineer at Amazon", "use_case": "AI coding at work", "switched_from": "", "story": "Ask HN: How is AI-assisted coding going for you professionally?"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49589914", "title": "Ask HN: How do you manage skills files?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49535284", "title": "Can I opt out of my input or output data being used for training?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49233423", "title": "Ask HN: What are you working on? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49225778", "title": "How to write production-quality code with AI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48977128", "title": "Who's Afraid of Chinese Models?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48809877", "title": "GLM 5.2 and the coming AI margin collapse", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"neutral": 1, "recommend": 1}, "2026-03": {}, "2026-04": {"recommend": 1}, "2026-05": {}, "2026-06": {"neutral": 2}, "2026-07": {"neutral": 2, "recommend": 1}, "2026-08": {"neutral": 2}, "2026-09": {"neutral": 2}, "2026-10": {}}, "quotes": [{"id": 793511329, "item_id": 49594458, "url": "https://news.ycombinator.com/item?id=49594458", "by": "ygjb", "date": "2026-09-07", "stance": "neutral", "quote": "installed via post session hooks in Claude and Kiro", "excerpt": "So the term used internally is to make things \"Determinishtic\". I use skills extensively, combined with SOPs, scripts and MCP servers. An example skill I have is SessionMiner, which is installed via post session hooks in Claude and Kiro, and analyzes the session, what was accomplished, and whether or not it should be turned into a skill, then when it summarizes it, the decisions it came to and either fires off a mess", "context": "uses skills, SOPs, scripts and MCP servers extensively", "use_case": "skills and session analysis", "switched_from": "", "story": "Ask HN: How do you manage skills files?"}, {"id": 792587298, "item_id": 49536706, "url": "https://news.ycombinator.com/item?id=49536706", "by": "jnurmine", "date": "2026-09-02", "stance": "neutral", "quote": "Claude (in Kiro)", "excerpt": "To be honest, I have a hard time noticing differences with Claude (in Kiro) and Mistral Vibe, at least with what I use them for. They simply feel like talking to the exact same thing.", "context": "", "use_case": "coding with Claude", "switched_from": "", "story": "Can I opt out of my input or output data being used for training?"}, {"id": 787860050, "item_id": 49241253, "url": "https://news.ycombinator.com/item?id=49241253", "by": "gabosarmiento", "date": "2026-08-10", "stance": "neutral", "quote": "with an skill for Kiro or Claude Code", "excerpt": "I wanted to create some demos for showcasing my app with Claude. So I created [Demotape] a screen recording app for MacOs (with an skill for Kiro or Claude Code) so it can inspect your project, plan the scenes, operate the browser, record the demo, and add synchronized narration and captions(w/ OpeanAI, ElevenLabs or run your model locally with docker). Free app available on: https://github.com/gabosarmiento/demotape", "context": "", "use_case": "agent skill for demo creation", "switched_from": "", "story": "Ask HN: What are you working on? (August 2026)"}, {"id": 787612468, "item_id": 49225779, "url": "https://news.ycombinator.com/item?id=49225779", "by": "Ovid", "date": "2026-08-08", "stance": "neutral", "quote": "My professional setup is Kiro with PAAD and some personal skills and powers.", "excerpt": "Many people trying to develop software treat AI as magic pixie dust they can sprinkle on a problem to make it go away. For coding, this as \"AI-led engineering.\" The literature is rife with the failures of this. Instead, I argue that we need to bring back well-known engineering best practices and treat AI as a tool to support them. This is \"engineering-led AI.\" I created a free, online tutorial to explain this approac", "context": "", "use_case": "professional AI coding", "switched_from": "", "story": "How to write production-quality code with AI"}, {"id": 783813874, "item_id": 48988367, "url": "https://news.ycombinator.com/item?id=48988367", "by": "Aperocky", "date": "2026-07-20", "stance": "neutral", "quote": "I use a mixture of claude code and codex and kiro as my swarm.", "excerpt": "I use a mixture of claude code and codex and kiro as my swarm. They communicate through my own harness, and it's working pretty well so far. claude code is being overtaken by codex however because I noticed lately the accuracy of the latter is the best.", "context": "", "use_case": "coding agent in a swarm", "switched_from": "", "story": "Who's Afraid of Chinese Models?"}, {"id": 781022240, "item_id": 48813890, "url": "https://news.ycombinator.com/item?id=48813890", "by": "danny_codes", "date": "2026-07-06", "stance": "recommend", "quote": "I switched to Kiro and it's essentially identical.. well a bit better because you get a better idea of what the harness is doing", "excerpt": "Is it? I switched to Kiro and it's essentially identical.. well a bit better because you get a better idea of what the harness is doing, but otherwise identical.", "context": "", "use_case": "AI coding harness", "switched_from": "", "story": "GLM 5.2 and the coming AI margin collapse"}, {"id": 780535363, "item_id": 48783460, "url": "https://news.ycombinator.com/item?id=48783460", "by": "jnurmine", "date": "2026-07-04", "stance": "neutral", "quote": "I use Claude with Kiro at work", "excerpt": "I use Claude with Kiro at work and at home Mistral stuff with pro subscription for coding and research. I don't see a fundamental difference between them in results, at least with what I use them for. The cost is lower too, but it is not the only reason why I won't use Claude at home. Vibe (the CLI Kiro-like tool) feels more \"Claude-ish\" as it has more terse answers, while the Le Chat can get quite chatty if you real", "context": "", "use_case": "work coding", "switched_from": "", "story": "Leanstral 1.5"}, {"id": 777807185, "item_id": 48612949, "url": "https://news.ycombinator.com/item?id=48612949", "by": "ratio53", "date": "2026-06-20", "stance": "neutral", "quote": "At work we only have access to claude / kiro.", "excerpt": "At work we only have access to claude / kiro. I only use it via cli since I find this to be the most flexible setup as claude can find stuff anywhere, read, write and run programs etc.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Ask HN: Do you use Claude Code, Codex, or something else?"}, {"id": 776335264, "item_id": 48520954, "url": "https://news.ycombinator.com/item?id=48520954", "by": "astqs", "date": "2026-06-13", "stance": "neutral", "quote": "I used Kiro in December and I burnt through 200 eur worth of tokens in a weekend.", "excerpt": "I used Kiro in December and I burnt through 200 eur worth of tokens in a weekend. Ultimately it was money well-spent, but, I think that if you want, you can spend as much compute as you have access to. Will it be efficient use of tokens? Probably not. From all the data, it looks like the 200usd we pay for monthly usage is subsidised\u2026 at break-even pricing \u2026 well, that 200 is starting to look like a few thousand.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "AI Coding at Home Without Going Broke"}, {"id": 766837968, "item_id": 47927373, "url": "https://news.ycombinator.com/item?id=47927373", "by": "topce", "date": "2026-04-27", "stance": "recommend", "quote": "IMHO lot of people will switch to kiro and or deep seek", "excerpt": "I used both copilot and kiro copilot sonet 1 copilot opus 3 kiro sonet 1.3 kiro opus 2.2 IMHO lot of people will switch to kiro and or deep seek it look like AWS done best inference google is another big player , has model and also cloud byt my 2 cents form Cents on AWS", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Microsoft to Stop Sharing Revenue with Main AI Partner OpenAI"}, {"id": 753727216, "item_id": 47107951, "url": "https://news.ycombinator.com/item?id=47107951", "by": "achenatx", "date": "2026-02-21", "stance": "recommend", "quote": "I can let it run for an hour or more in this mode. Then there is lots of stuff to fix, but it is mostly correct.", "excerpt": "I use amazon kiro. The AI first works with you to write requirements, then it produces a design, then a task list. The helps the AI to make smaller chunks to work on, it will work on one task at a time. I can let it run for an hour or more in this mode. Then there is lots of stuff to fix, but it is mostly correct. Kiro also supports steering files, they are files that try to lock the AI in for common design decisions", "context": "", "use_case": "spec-driven AI coding", "switched_from": "", "story": "How I use Claude Code: Separation of planning and execution"}, {"id": 751990160, "item_id": 46999385, "url": "https://news.ycombinator.com/item?id=46999385", "by": "mlaretallack", "date": "2026-02-12", "stance": "neutral", "quote": "each with there own version of AWS Kiro, and each kiro has its own project I am working on", "excerpt": "Not the best way to do it, but I use xfce, multiple workspaces, each with there own version of AWS Kiro, and each kiro has its own project I am working on. This allows me to \"switch context\" easier between each project to check how the agents are getting on. Kiro also notifies me when an agent wants somthing. Usually I keep it to about 4 projects at a time, just to keep the context switching down.", "context": "runs about 4 projects at a time", "use_case": "parallel coding agents per project", "switched_from": "", "story": "Ask HN: Are you using an agent orchestrator to write code?"}]}