{"slug": "bmad", "name": "BMAD", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 4, "commenters": 4, "warners": 0, "score": 3.601, "rising": 0.02, "first": "2025-11-16", "latest": "2026-10-12", "why": "a good framework that follows \"AI Agentic Agile Methodology\", and specification driven development is BMAD. Really helpful for brainstorming sessions.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 0, "compare": 0, "warn": 0}, "spark": [1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1], "listed": true, "loved": [], "caveat": "", "short_quote": "a good framework that follows \"AI Agentic Agile Methodology\", and specification driven development is BMAD. Really helpful for brainstorming sessions.", "icon": true, "domain": null, "github_repo": "github.com/bmad-code-org/bmad-method", "official_url": "https://github.com/bmad-code-org/BMAD-METHOD", "pricing": "", "aliases": ["BMAD", "BMAD method", "BMAD-METHOD"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 800792740, "item_id": 50049546, "url": "https://news.ycombinator.com/item?id=50049546", "by": "joaoviniciusgs", "date": "2026-10-12", "stance": "recommend", "quote": "I'm genuinely surprised by how competent even a mediocre AI model can become when you give it a decent framework to work with.", "excerpt": "So yeah, I made a clone of Boom 3D. If you don't know what Boom 3D is, it's an audio enhancement app available on Steam and other stores that makes your headphones sound more immersive with 3D spatial audio and other audio effects. It's called OpenBoom, and it's an open-source alternative for Windows built with Rust and Tauri. It aims to bring features like 3D spatial audio, a 31-band equalizer, AutoEq headphone prof", "context": "", "use_case": "planning and building apps with AI", "switched_from": "", "story": "I made an open-source Boom 3D clone. Wanna check it out?"}, {"id": 779389793, "item_id": 48711862, "url": "https://news.ycombinator.com/item?id=48711862", "by": "matt3D", "date": "2026-06-28", "stance": "recommend", "quote": "my go to is the BMAD method", "excerpt": "I find it a bit odd that none of the comments so far have mentioned LLMs. Astro with a good understanding of how to build using a coding agent (my go to is the BMAD method)", "context": "", "use_case": "agentic development workflow", "switched_from": "", "story": "Ask HN: Is WordPress the best way to create new websites for beginner"}, {"id": 766458160, "item_id": 47903635, "url": "https://news.ycombinator.com/item?id=47903635", "by": "sminchev", "date": "2026-04-25", "stance": "recommend", "quote": "I used BMAD for this. It created a specification for me", "excerpt": "> One of the reasons the AI fails constantly is that it has no context of the entire code base. I had the same issue, take your time and describe the context. Create a documentation out of the project. I used BMAD for this. It created a specification for me, by checking the code I answered a lot of questions, clarified a lot of things. And once I had this done, I now start each session with: read the documents, prepa", "context": "working on a large legacy codebase", "use_case": "documenting legacy codebase", "switched_from": "", "story": "Ask HN: How are you using AI code assistants on large messy legacy code bases?"}, {"id": 764118912, "item_id": 47757432, "url": "https://news.ycombinator.com/item?id=47757432", "by": "sminchev", "date": "2026-04-13", "stance": "recommend", "quote": "a good framework that follows \"AI Agentic Agile Methodology\", and specification driven development is BMAD. Really helpful for brainstorming sessions.", "excerpt": "I like it, I use it, I see high potential. It is not perfect, but it gives good results. Sometimes, we joke with colleagues, that somebody re-invented the hot water: specification-driven development. AI, or human, in order to give good results, it needs good specification. In some cases, AI can even be better than a usual developer. In my case, I don't know Kotlin, but I am a software developer, and my expertise was ", "context": "software developer", "use_case": "spec-driven AI development", "switched_from": "", "story": "Why Engineering Teams Need an Agentic Layer, Not Just AI Chat"}, {"id": 764103569, "item_id": 47756473, "url": "https://news.ycombinator.com/item?id=47756473", "by": "sminchev", "date": "2026-04-13", "stance": "recommend", "quote": "It has really nice agents that can help with brainstorm session, UI/UX, Security, architecture, documentation", "excerpt": "Opus is OK, but I would suggest to use also frameworks, like BMAD. It has really nice agents that can help with brainstorm session, UI/UX, Security, architecture, documentation, and all needed so that the the system has good basis before development. It is expensive, I know. I mean, it takes a lot of tokens and the $20 is just not enough, but the price worth it, in my opinion. I did it with my project. I tried, Gemin", "context": "", "use_case": "agentic planning framework", "switched_from": "", "story": "Ask HN: What's the best AI model for system design nowadays?"}]}], "caveats": [], "who": [{"by": "sminchev", "context": "working on a large legacy codebase", "url": "https://news.ycombinator.com/item?id=47903635", "date": "2026-04-25"}, {"by": "atilla_bilgic", "context": "former senior solution architect", "url": "https://news.ycombinator.com/item?id=45951505", "date": "2025-11-16"}], "tags": [], "use_cases": ["planning and building apps with ai", "agentic development workflow", "documenting legacy codebase", "spec-driven ai development", "agentic planning framework", "spec-driven ai agent workflow"], "compared": [{"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=50049545", "title": "I made an open-source Boom 3D clone. Wanna check it out?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48709796", "title": "Ask HN: Is WordPress the best way to create new websites for beginner", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47890749", "title": "Ask HN: How are you using AI code assistants on large messy legacy code bases?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47757218", "title": "Why Engineering Teams Need an Agentic Layer, Not Just AI Chat", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47753223", "title": "Ask HN: What's the best AI model for system design nowadays?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47543324", "title": "Ask HN: What do you use for normative specs to drive AI agents?", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {"recommend": 1}, "2026-05": {}, "2026-06": {"recommend": 1}, "2026-07": {}, "2026-08": {}, "2026-09": {}, "2026-10": {"recommend": 1}}, "quotes": [{"id": 800792740, "item_id": 50049546, "url": "https://news.ycombinator.com/item?id=50049546", "by": "joaoviniciusgs", "date": "2026-10-12", "stance": "recommend", "quote": "I'm genuinely surprised by how competent even a mediocre AI model can become when you give it a decent framework to work with.", "excerpt": "So yeah, I made a clone of Boom 3D. If you don't know what Boom 3D is, it's an audio enhancement app available on Steam and other stores that makes your headphones sound more immersive with 3D spatial audio and other audio effects. It's called OpenBoom, and it's an open-source alternative for Windows built with Rust and Tauri. It aims to bring features like 3D spatial audio, a 31-band equalizer, AutoEq headphone prof", "context": "", "use_case": "planning and building apps with AI", "switched_from": "", "story": "I made an open-source Boom 3D clone. Wanna check it out?"}, {"id": 779389793, "item_id": 48711862, "url": "https://news.ycombinator.com/item?id=48711862", "by": "matt3D", "date": "2026-06-28", "stance": "recommend", "quote": "my go to is the BMAD method", "excerpt": "I find it a bit odd that none of the comments so far have mentioned LLMs. Astro with a good understanding of how to build using a coding agent (my go to is the BMAD method)", "context": "", "use_case": "agentic development workflow", "switched_from": "", "story": "Ask HN: Is WordPress the best way to create new websites for beginner"}, {"id": 766458160, "item_id": 47903635, "url": "https://news.ycombinator.com/item?id=47903635", "by": "sminchev", "date": "2026-04-25", "stance": "recommend", "quote": "I used BMAD for this. It created a specification for me", "excerpt": "> One of the reasons the AI fails constantly is that it has no context of the entire code base. I had the same issue, take your time and describe the context. Create a documentation out of the project. I used BMAD for this. It created a specification for me, by checking the code I answered a lot of questions, clarified a lot of things. And once I had this done, I now start each session with: read the documents, prepa", "context": "working on a large legacy codebase", "use_case": "documenting legacy codebase", "switched_from": "", "story": "Ask HN: How are you using AI code assistants on large messy legacy code bases?"}, {"id": 764118912, "item_id": 47757432, "url": "https://news.ycombinator.com/item?id=47757432", "by": "sminchev", "date": "2026-04-13", "stance": "recommend", "quote": "a good framework that follows \"AI Agentic Agile Methodology\", and specification driven development is BMAD. Really helpful for brainstorming sessions.", "excerpt": "I like it, I use it, I see high potential. It is not perfect, but it gives good results. Sometimes, we joke with colleagues, that somebody re-invented the hot water: specification-driven development. AI, or human, in order to give good results, it needs good specification. In some cases, AI can even be better than a usual developer. In my case, I don't know Kotlin, but I am a software developer, and my expertise was ", "context": "software developer", "use_case": "spec-driven AI development", "switched_from": "", "story": "Why Engineering Teams Need an Agentic Layer, Not Just AI Chat"}, {"id": 764103569, "item_id": 47756473, "url": "https://news.ycombinator.com/item?id=47756473", "by": "sminchev", "date": "2026-04-13", "stance": "recommend", "quote": "It has really nice agents that can help with brainstorm session, UI/UX, Security, architecture, documentation", "excerpt": "Opus is OK, but I would suggest to use also frameworks, like BMAD. It has really nice agents that can help with brainstorm session, UI/UX, Security, architecture, documentation, and all needed so that the the system has good basis before development. It is expensive, I know. I mean, it takes a lot of tokens and the $20 is just not enough, but the price worth it, in my opinion. I did it with my project. I tried, Gemin", "context": "", "use_case": "agentic planning framework", "switched_from": "", "story": "Ask HN: What's the best AI model for system design nowadays?"}, {"id": 761061200, "item_id": 47566325, "url": "https://news.ycombinator.com/item?id=47566325", "by": "sminchev", "date": "2026-03-29", "stance": "recommend", "quote": "I use BMAD, and I don't care how the markdown files look like.", "excerpt": "I use BMAD, and I don't care how the markdown files look like. I don't read them. I ask agents to create and read the files. One agent create the technical specification in markdown file, and a dev agent reads it and process it. ;) If I need something to distribute or read myself, I ask for a pdf copy :)", "context": "", "use_case": "spec-driven AI agent workflow", "switched_from": "", "story": "Ask HN: What do you use for normative specs to drive AI agents?"}, {"id": 735224080, "item_id": 45951505, "url": "https://news.ycombinator.com/item?id=45951505", "by": "atilla_bilgic", "date": "2025-11-16", "stance": "recommend", "quote": "This framework is a well thought approach to create very detailed definitions of the tasks", "excerpt": "Hi, As a former senior solution architect, I have tested several tools or platforms of \"vibe-coding\" or \"agentic software development\". None of the available tools or platforms satisfied the quality level, I used to have. Number of failures was more than successes. Which is completely understandable for the \"Sophisticated Prediction Algorithms\" or LLMs in official terms. The main problem is these systems do not have ", "context": "former senior solution architect", "use_case": "structuring tasks for coding agents", "switched_from": "", "story": "Startup CTO insisting on only vibe coding \u2013 What to do?"}]}