Developer tools · agent framework
BMAD Method
Hacker Approved
Gives AI coding agents detailed rules, specs and agent roles for structured projects. Common caveat: it gets code most of the way to production-ready, and critics find its process heavy.
Summarized from 22 comments.
Gives AI coding agents detailed rules, specs and agent roles for structured projects. Common caveat: it gets code most of the way to production-ready, and critics find its process heavy.
- recommend
- 14
- criticize
- 4
- months recommended
- 8 of 13
Why people love it
Detailed task rules and specs for agents · 4
This framework is a well thought approach to create very detailed definitions of the tasks that LLM based coding agents can process
Nov 2025 · commentFrameworks like BMAD has been great at enabling developers adopt spec driven development with AI.
May 2026 · commentin BMAD you can create files where all the rules, architectures, DOs and DON'Ts are covered
Apr 2026 · commentUseful for planning and brainstorming · 2
I've been using BMAD for planning and speccing out something fairly elaborate, and it's been a blast.
Mar 2026 · commentReally helpful for brainstorming sessions.
Apr 2026 · commentAgent roles like a product team · 2
These agents are crucial because it’s like having a whole Product department inside your codebase
Mar 2026 · commentYou should review the BMAD method, especially the Analyst agent.
Nov 2025 · commentWorks on complex real projects · 2
I'm successfully using frameworks like bmad to deliver complex apps at that level.
May 2026 · commentis really good and I've onboarded a few Saas projects into it now
May 2026 · comment
What people warn about
Heavy process and ceremony · 3
every story requires running through create → develop → test → review → fix → update status
Feb 2026 · commentBasically, it's Waterfall for Agents. Lots of Capitalized Words to signify something.
Mar 2026 · commentBoth had what seemed like unnecessary ceremony around the specs
May 2026 · comment
What hackers pick instead
- Claude Agent SDKDevelopers praise it for building agents on top of Claude Code at a predictable cost. Critics agree the main caveat is Anthropic's shifting rules on using subscriptions with it.36recommend
- LangChainRecommended for easy switching between LLM providers and many integrations; critics find it bloated, overly abstract, and built for older models.32recommend
- MastraOpen-source TypeScript framework for building AI agents, praised for workflow primitives and developer experience. Common caveat: its opinionated patterns can slow you down when your project doesn't fit them.32recommend
- LangGraphRecommended for deterministic, stateful agent workflows with graph-based control, human-in-the-loop and time travel. Critics find it rigid and overly complex for simple tasks.31recommend
- DSPyPeople use it to structure LLM calls as typed programs and optimize prompts. Critics say its value depends on a good automated metric and up-front setup.29recommend
Every quote
The 20 most detailed of 22 comments. Each links to the original.
This framework is a well thought approach to create very detailed definitions of the tasks that LLM based coding agents can process
Recommends · Nov 2025 · in “Startup CTO insisting on only vibe coding – What to do?”
I've been using BMAD for planning and speccing out something fairly elaborate, and it's been a blast.
Recommends · Mar 2026 · in “I'm 60 years old. Claude Code has ignited a passion again”
These agents are crucial because it’s like having a whole Product department inside your codebase
Recommends · Mar 2026 · in “We've got 10 sales from Hacker News”
Frameworks like BMAD has been great at enabling developers adopt spec driven development with AI.
Recommends · May 2026 · in “Vibe Coding Is Becoming an Osint Risk”
every story requires running through create → develop → test → review → fix → update status
Mixed · Feb 2026
in BMAD you can create files where all the rules, architectures, DOs and DON'Ts are covered
Recommends · Apr 2026 · in “Why AI Coding Tools Still Feel Stuck on Localhost”
It created a specification for me, by checking the code I answered a lot of questions
Recommends · Apr 2026 · in “Ask HN: How are you using AI code assistants on large messy legacy code bases?”
I'm successfully using frameworks like bmad to deliver complex apps at that level.
Recommends · May 2026 · in “OpenClaw Creator Spent $1.3M on OpenAI Tokens in 30 Days”
is really good and I've onboarded a few Saas projects into it now
Recommends · May 2026 · in “Agentic Coding Is a Trap”
You should review the BMAD method, especially the Analyst agent.
Recommends · Nov 2025 · in “Ask HN: What are you working on?”
Really helpful for brainstorming sessions.
Recommends · Apr 2026 · in “Why Engineering Teams Need an Agentic Layer, Not Just AI Chat”
Basically, it's Waterfall for Agents. Lots of Capitalized Words to signify something.
Criticizes · Mar 2026 · in “Agentic Engineering Patterns”
Both had what seemed like unnecessary ceremony around the specs
Criticizes · May 2026 · in “Specsmaxxing – On overcoming AI psychosis, and why I write specs in YAML”
I'm genuinely surprised by how competent even a mediocre AI model can become when you give it a decent framework
Recommends · Oct 2026 · in “I made an open-source Boom 3D clone. Wanna check it out?”
My only concern is that it's able to get 90% of the way there for productionized ready code
Mixed · Jan 2026 · in “Claude Code's new hidden feature: Swarms”
but the price worth it, in my opinion. I did it with my project.
Recommends · Apr 2026 · in “Ask HN: What's the best AI model for system design nowadays?”
I use BMAD, and I don't care how the markdown files look like.
Recommends · Mar 2026 · in “Ask HN: What do you use for normative specs to drive AI agents?”
I've had positive experience with this (with Opus 4.7).
Recommends · Apr 2026 · in “Changes in the system prompt between Claude Opus 4.6 and 4.7”
my go to is the BMAD method
Recommends · Jun 2026 · in “Ask HN: Is WordPress the best way to create new websites for beginner”
which suffers from same issues, like Speckit and others
Criticizes · Mar 2026 · in “Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System”
Counts from 1,795,640 Hacker News comments, Nov 2025 to Nov 2026. How we count · Report a mistake