{"slug": "openspec", "name": "OpenSpec", "category": "ai-coding", "category_name": "AI coding tools", "description": "Open-source spec-driven development framework that structures AI coding agent work into proposals, designs and tasks.", "recommenders": 11, "commenters": 17, "warners": 1, "score": 10.323, "rising": 8.02, "first": "2026-03-17", "latest": "2026-10-15", "why": "Liked for forcing upfront planning through a proposal, design and task flow before an agent writes code, and for keeping coding agents on track with specs committed alongside the code.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 13, "neutral": 5, "compare": 1, "warn": 1}, "spark": [0, 0, 0, 0, 1, 1, 0, 0, 1, 3, 5, 2], "listed": true, "loved": ["Upfront planning", "Constrains agents"], "caveat": "Spec drift", "short_quote": "Easily my favorite spec driven development framework.", "icon": true, "domain": "openspec.dev", "github_repo": null, "official_url": "https://openspec.dev/", "pricing": "open source", "aliases": ["OpenSpec"], "verdict": [{"text": "Liked for forcing upfront planning through a proposal, design and task flow before an agent writes code", "cites": [{"id": 795788848, "item_id": 49736803, "url": "https://news.ycombinator.com/item?id=49736803", "by": "jochem9", "date": "2026-09-17", "stance": "recommend", "quote": "The power is that you do a lot of upfront thinking.", "excerpt": "I use it at a much smaller scale. I think that's also the right place, because its a CLI tool + skills that generate md files. Not something you'd give to a business person. I start from a single ticket (sometimes just a handful of changes, but I want the spec as docs) to changes that you'd normally split over several tickets. Basically the flow proposal -> design -> specs -> tasks gives you and AI a method to build ", "context": "uses it on a small team with PR review", "use_case": "spec-driven AI development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 800405904, "item_id": 50025369, "url": "https://news.ycombinator.com/item?id=50025369", "by": "Zambyte", "date": "2026-10-09", "stance": "recommend", "quote": "I use a tool called openspec to drive the framework of creating proposal, design, and task documents, ahead of driving the implementation.", "excerpt": "> Otherwise it\u2019s all a black box. You ask for something, code comes out, and you hope it does what you meant. It's easy to argue against the worst example of something. Using AI to program can be done well, or it can be done poorly. Using compilers and interpreters to program can be done well or poorly as well. There is nothing fundamental about AI programming that limits programmer comprehension, care, or influence ", "context": "", "use_case": "spec-driven development with AI agents", "switched_from": "", "story": "We Are Not All Terrible Developers"}, {"id": 788999152, "item_id": 49312447, "url": "https://news.ycombinator.com/item?id=49312447", "by": "guilyguily", "date": "2026-08-15", "stance": "recommend", "quote": "I use openspec in addition with the /grill-me skill and it really helps clearing the path before starting to code.", "excerpt": "I use openspec in addition with the /grill-me skill and it really helps clearing the path before starting to code. I think the goal of engineering, when using AI, is to maximize your value upfront instead of every five minutes.", "context": "", "use_case": "spec-driven AI coding", "switched_from": "", "story": "The AI Situation in Software Development"}, {"id": 766356961, "item_id": 47897310, "url": "https://news.ycombinator.com/item?id=47897310", "by": "arikrahman", "date": "2026-04-24", "stance": "recommend", "quote": "using Open Spec to negotiate requirements before the handoff, has helped me a lot", "excerpt": "I use Aider nowadays, and will probably cancel my Github multi AI bundle subscription due to the new training policy. I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "context": "", "use_case": "negotiating requirements before coding", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}]}, {"text": ", and for keeping coding agents on track with specs committed alongside the code.", "cites": [{"id": 795767952, "item_id": 49735497, "url": "https://news.ycombinator.com/item?id=49735497", "by": "alexjplant", "date": "2026-09-17", "stance": "recommend", "quote": "Using OpenSpec keeps things as constrained as possible with the side effect of recording what your system does.", "excerpt": "I bother because Claude Code does wacky nonsense unless I use OpenSpec (or something similar) to explicitly research, scope, persist, then implement in a brand-new context. Even Opus will do ridiculous nonsense like throw its hands up when asked to start a Docker container, ignore explicit architectural instructions, write verbose make-work documentation riddled with inaccuracies, etc. Using OpenSpec keeps things as ", "context": "constrained by regulations at day job", "use_case": "constraining coding agents", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 791904672, "item_id": 49494042, "url": "https://news.ycombinator.com/item?id=49494042", "by": "fcarraldo", "date": "2026-08-29", "stance": "recommend", "quote": "we all agreed to use OpenSpec early on, and to commit the specs alongside the code", "excerpt": "I\u2019ve had a good experience with a greenfield project. The single thing that seems to have helped is that we all agreed to use OpenSpec early on, and to commit the specs alongside the code. I have no affiliation with OpenSpec and I don\u2019t suspect it\u2019s doing anything unique here, but having the intent develop alongside the code in the repository seems to have ensured that agents have a more holistic view of the project.", "context": "Team on a greenfield project, no affiliation", "use_case": "spec-driven agent development", "switched_from": "", "story": "Domain-Driven Agents"}, {"id": 795759424, "item_id": 49734964, "url": "https://news.ycombinator.com/item?id=49734964", "by": "honkycat", "date": "2026-09-17", "stance": "recommend", "quote": "Easily my favorite spec driven development framework.", "excerpt": "LOVE. LOVE. LOVE. Openspec. Easily my favorite spec driven development framework. It scored really well in our internal evals as well. I think it has the most sane ceremony and its model fits my mental model really well. I've also been working on a TUI that will automatically generate \"phases\" with each one being a openspec spec. I would highly recommend trying out SpecDriven development. I found it to be the most pr", "context": "", "use_case": "spec-driven development with LLMs", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"text": " The main caveat is that specs can drift far from the code on long projects", "cites": [{"id": 795822992, "item_id": 49738937, "url": "https://news.ycombinator.com/item?id=49738937", "by": "mafro", "date": "2026-09-17", "stance": "neutral", "quote": "What I did find very useful and have retained is the process flow.", "excerpt": "I've used OpenSpec extensively on two large pieces of software which were worked solo over 6-9 months. Recently, I've completely ditched the specification part. I found they just weren't useful over the longer term. I used an LLM to assess in both directions whether the code matched the specs and whether the specs matched the code. On both software projects this came out with huge divergence from spec to code. Basica", "context": "solo developer on two large projects", "use_case": "spec-driven development with LLM", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"text": ", and one commenter found the documentation links confusing.", "cites": [{"id": 795753488, "item_id": 49734593, "url": "https://news.ycombinator.com/item?id=49734593", "by": "CharlieDigital", "date": "2026-09-16", "stance": "warn", "quote": "Somehow not very confidence inspiring...", "excerpt": "This section https://openspec.dev/docs/setup links to \"Concepts\" Concepts links here: https://github.com/Fission-AI/OpenSpec/blob/main/docs-lab/guides/concepts.md All the docs here are the templates rather than the actual file (I presume: https://github.com/Fission-AI/OpenSpec/blob/main/docs/concepts.md) Somehow not very confidence inspiring...", "context": "", "use_case": "", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}], "praise": [{"label": "Upfront planning", "summary": "The proposal, design, specs and tasks flow helps users think through and agree on a change before implementation.", "quotes": [{"id": 795788848, "item_id": 49736803, "url": "https://news.ycombinator.com/item?id=49736803", "by": "jochem9", "date": "2026-09-17", "stance": "recommend", "quote": "The power is that you do a lot of upfront thinking.", "excerpt": "I use it at a much smaller scale. I think that's also the right place, because its a CLI tool + skills that generate md files. Not something you'd give to a business person. I start from a single ticket (sometimes just a handful of changes, but I want the spec as docs) to changes that you'd normally split over several tickets. Basically the flow proposal -> design -> specs -> tasks gives you and AI a method to build ", "context": "uses it on a small team with PR review", "use_case": "spec-driven AI development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 788999152, "item_id": 49312447, "url": "https://news.ycombinator.com/item?id=49312447", "by": "guilyguily", "date": "2026-08-15", "stance": "recommend", "quote": "I use openspec in addition with the /grill-me skill and it really helps clearing the path before starting to code.", "excerpt": "I use openspec in addition with the /grill-me skill and it really helps clearing the path before starting to code. I think the goal of engineering, when using AI, is to maximize your value upfront instead of every five minutes.", "context": "", "use_case": "spec-driven AI coding", "switched_from": "", "story": "The AI Situation in Software Development"}, {"id": 766356961, "item_id": 47897310, "url": "https://news.ycombinator.com/item?id=47897310", "by": "arikrahman", "date": "2026-04-24", "stance": "recommend", "quote": "using Open Spec to negotiate requirements before the handoff, has helped me a lot", "excerpt": "I use Aider nowadays, and will probably cancel my Github multi AI bundle subscription due to the new training policy. I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "context": "", "use_case": "negotiating requirements before coding", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}]}, {"label": "Constrains agents", "summary": "Users say it keeps agents like Claude Code focused and gives them a fuller view of the project.", "quotes": [{"id": 795767952, "item_id": 49735497, "url": "https://news.ycombinator.com/item?id=49735497", "by": "alexjplant", "date": "2026-09-17", "stance": "recommend", "quote": "Using OpenSpec keeps things as constrained as possible with the side effect of recording what your system does.", "excerpt": "I bother because Claude Code does wacky nonsense unless I use OpenSpec (or something similar) to explicitly research, scope, persist, then implement in a brand-new context. Even Opus will do ridiculous nonsense like throw its hands up when asked to start a Docker container, ignore explicit architectural instructions, write verbose make-work documentation riddled with inaccuracies, etc. Using OpenSpec keeps things as ", "context": "constrained by regulations at day job", "use_case": "constraining coding agents", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 791904672, "item_id": 49494042, "url": "https://news.ycombinator.com/item?id=49494042", "by": "fcarraldo", "date": "2026-08-29", "stance": "recommend", "quote": "we all agreed to use OpenSpec early on, and to commit the specs alongside the code", "excerpt": "I\u2019ve had a good experience with a greenfield project. The single thing that seems to have helped is that we all agreed to use OpenSpec early on, and to commit the specs alongside the code. I have no affiliation with OpenSpec and I don\u2019t suspect it\u2019s doing anything unique here, but having the intent develop alongside the code in the repository seems to have ensured that agents have a more holistic view of the project.", "context": "Team on a greenfield project, no affiliation", "use_case": "spec-driven agent development", "switched_from": "", "story": "Domain-Driven Agents"}, {"id": 795759424, "item_id": 49734964, "url": "https://news.ycombinator.com/item?id=49734964", "by": "honkycat", "date": "2026-09-17", "stance": "recommend", "quote": "Easily my favorite spec driven development framework.", "excerpt": "LOVE. LOVE. LOVE. Openspec. Easily my favorite spec driven development framework. It scored really well in our internal evals as well. I think it has the most sane ceremony and its model fits my mental model really well. I've also been working on a TUI that will automatically generate \"phases\" with each one being a openspec spec. I would highly recommend trying out SpecDriven development. I found it to be the most pr", "context": "", "use_case": "spec-driven development with LLMs", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"label": "Specs as documentation", "summary": "Committing specs with the code records intent and what the system does.", "quotes": [{"id": 791904672, "item_id": 49494042, "url": "https://news.ycombinator.com/item?id=49494042", "by": "fcarraldo", "date": "2026-08-29", "stance": "recommend", "quote": "we all agreed to use OpenSpec early on, and to commit the specs alongside the code", "excerpt": "I\u2019ve had a good experience with a greenfield project. The single thing that seems to have helped is that we all agreed to use OpenSpec early on, and to commit the specs alongside the code. I have no affiliation with OpenSpec and I don\u2019t suspect it\u2019s doing anything unique here, but having the intent develop alongside the code in the repository seems to have ensured that agents have a more holistic view of the project.", "context": "Team on a greenfield project, no affiliation", "use_case": "spec-driven agent development", "switched_from": "", "story": "Domain-Driven Agents"}, {"id": 795767952, "item_id": 49735497, "url": "https://news.ycombinator.com/item?id=49735497", "by": "alexjplant", "date": "2026-09-17", "stance": "recommend", "quote": "Using OpenSpec keeps things as constrained as possible with the side effect of recording what your system does.", "excerpt": "I bother because Claude Code does wacky nonsense unless I use OpenSpec (or something similar) to explicitly research, scope, persist, then implement in a brand-new context. Even Opus will do ridiculous nonsense like throw its hands up when asked to start a Docker container, ignore explicit architectural instructions, write verbose make-work documentation riddled with inaccuracies, etc. Using OpenSpec keeps things as ", "context": "constrained by regulations at day job", "use_case": "constraining coding agents", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795788848, "item_id": 49736803, "url": "https://news.ycombinator.com/item?id=49736803", "by": "jochem9", "date": "2026-09-17", "stance": "recommend", "quote": "The power is that you do a lot of upfront thinking.", "excerpt": "I use it at a much smaller scale. I think that's also the right place, because its a CLI tool + skills that generate md files. Not something you'd give to a business person. I start from a single ticket (sometimes just a handful of changes, but I want the spec as docs) to changes that you'd normally split over several tickets. Basically the flow proposal -> design -> specs -> tasks gives you and AI a method to build ", "context": "uses it on a small team with PR review", "use_case": "spec-driven AI development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"label": "Light ceremony", "summary": "Commenters describe its process as sane and lighter than alternatives like GSD.", "quotes": [{"id": 795759424, "item_id": 49734964, "url": "https://news.ycombinator.com/item?id=49734964", "by": "honkycat", "date": "2026-09-17", "stance": "recommend", "quote": "Easily my favorite spec driven development framework.", "excerpt": "LOVE. LOVE. LOVE. Openspec. Easily my favorite spec driven development framework. It scored really well in our internal evals as well. I think it has the most sane ceremony and its model fits my mental model really well. I've also been working on a TUI that will automatically generate \"phases\" with each one being a openspec spec. I would highly recommend trying out SpecDriven development. I found it to be the most pr", "context": "", "use_case": "spec-driven development with LLMs", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795873504, "item_id": 49742094, "url": "https://news.ycombinator.com/item?id=49742094", "by": "_blk", "date": "2026-09-17", "stance": "compare", "quote": "How does it compare to GSD (opengsd.net)? Just from the command set it seems a lot lighter but also less expressive.", "excerpt": "Interesting project. How does it compare to GSD (opengsd.net)? Just from the command set it seems a lot lighter but also less expressive. GSD is quite OK but very token hungry (~4x but it buys traceability and has quite a powerful autonomous mode) I use gsd-meta-manager to manage multiple GSD projects in parallel without having to use a skill to query each project individually to see where they're at. Does openspec h", "context": "", "use_case": "AI spec framework", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"label": "Token savings", "summary": "Small per-task contexts fed into a loop script save tokens.", "quotes": [{"id": 795768384, "item_id": 49735524, "url": "https://news.ycombinator.com/item?id=49735524", "by": "recroad", "date": "2026-09-17", "stance": "recommend", "quote": "I use this to produce the task list which I then feed into a Ralph loop using a bash script.", "excerpt": "I use this to produce the task list which I then feed into a Ralph loop using a bash script. I save a lot of tokens since each tasks context is so small.", "context": "", "use_case": "producing task lists for agent loop", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"label": "Brownfield support", "summary": "One user prefers it because it also works on existing codebases.", "quotes": [{"id": 801642032, "item_id": 50102627, "url": "https://news.ycombinator.com/item?id=50102627", "by": "daitangio", "date": "2026-10-15", "stance": "recommend", "quote": "I prefer https://github.com/Fission-AI/OpenSpec because it works also on brown-field.", "excerpt": "I prefer https://github.com/Fission-AI/OpenSpec because it works also on brown-field. If you want an unbias-demo, take a look also at https://github.com/daitangio/take-ai-control/tree/demo/nello-openspec branch demo/nello-openspec", "context": "", "use_case": "spec-driven AI coding workflow", "switched_from": "", "story": "Aidlc: Adaptive workflow steering rules for AI coding agents"}]}], "caveats": [{"label": "Spec drift", "summary": "A solo user on two long projects found the specs diverged heavily from the code and dropped them, keeping only the process flow.", "quotes": [{"id": 795822992, "item_id": 49738937, "url": "https://news.ycombinator.com/item?id=49738937", "by": "mafro", "date": "2026-09-17", "stance": "neutral", "quote": "What I did find very useful and have retained is the process flow.", "excerpt": "I've used OpenSpec extensively on two large pieces of software which were worked solo over 6-9 months. Recently, I've completely ditched the specification part. I found they just weren't useful over the longer term. I used an LLM to assess in both directions whether the code matched the specs and whether the specs matched the code. On both software projects this came out with huge divergence from spec to code. Basica", "context": "solo developer on two large projects", "use_case": "spec-driven development with LLM", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"label": "Confusing docs", "summary": "Documentation links pointed to templates rather than the actual concept pages.", "quotes": [{"id": 795753488, "item_id": 49734593, "url": "https://news.ycombinator.com/item?id=49734593", "by": "CharlieDigital", "date": "2026-09-16", "stance": "warn", "quote": "Somehow not very confidence inspiring...", "excerpt": "This section https://openspec.dev/docs/setup links to \"Concepts\" Concepts links here: https://github.com/Fission-AI/OpenSpec/blob/main/docs-lab/guides/concepts.md All the docs here are the templates rather than the actual file (I presume: https://github.com/Fission-AI/OpenSpec/blob/main/docs/concepts.md) Somehow not very confidence inspiring...", "context": "", "use_case": "", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"label": "Less expressive", "summary": "One commenter thought its command set looked less expressive than GSD's.", "quotes": [{"id": 795873504, "item_id": 49742094, "url": "https://news.ycombinator.com/item?id=49742094", "by": "_blk", "date": "2026-09-17", "stance": "compare", "quote": "How does it compare to GSD (opengsd.net)? Just from the command set it seems a lot lighter but also less expressive.", "excerpt": "Interesting project. How does it compare to GSD (opengsd.net)? Just from the command set it seems a lot lighter but also less expressive. GSD is quite OK but very token hungry (~4x but it buys traceability and has quite a powerful autonomous mode) I use gsd-meta-manager to manage multiple GSD projects in parallel without having to use a skill to query each project individually to see where they're at. Does openspec h", "context": "", "use_case": "AI spec framework", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}, {"label": "Reasoning not captured", "summary": "The default schema does not record the reasoning behind decisions unless customized.", "quotes": [{"id": 791988688, "item_id": 49499293, "url": "https://news.ycombinator.com/item?id=49499293", "by": "alasano", "date": "2026-08-30", "stance": "recommend", "quote": "I use and love openspec", "excerpt": "I use and love openspec and I'm against this session attribution by default setting. But I do see the value in seeing the conversation that lead to the spec. I make sure that all product decisions go through me prior to the agent writing the spec and the questions I ask and decisions I make could definitely help understand retroactively why something is the way it is. I guess with the default openspec schema you woul", "context": "", "use_case": "spec-driven agent development", "switched_from": "", "story": "Claude Session URL appended to commit messages and PR descriptions by default"}]}, {"label": "Developer-oriented", "summary": "It is a CLI tool that generates Markdown files, not something to hand to business users.", "quotes": [{"id": 795788848, "item_id": 49736803, "url": "https://news.ycombinator.com/item?id=49736803", "by": "jochem9", "date": "2026-09-17", "stance": "recommend", "quote": "The power is that you do a lot of upfront thinking.", "excerpt": "I use it at a much smaller scale. I think that's also the right place, because its a CLI tool + skills that generate md files. Not something you'd give to a business person. I start from a single ticket (sometimes just a handful of changes, but I want the spec as docs) to changes that you'd normally split over several tickets. Basically the flow proposal -> design -> specs -> tasks gives you and AI a method to build ", "context": "uses it on a small team with PR review", "use_case": "spec-driven AI development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}]}], "who": [{"by": "mafro", "context": "solo developer on two large projects", "url": "https://news.ycombinator.com/item?id=49738937", "date": "2026-09-17"}, {"by": "jochem9", "context": "uses it on a small team with PR review", "url": "https://news.ycombinator.com/item?id=49736803", "date": "2026-09-17"}, {"by": "alexjplant", "context": "constrained by regulations at day job", "url": "https://news.ycombinator.com/item?id=49735497", "date": "2026-09-17"}, {"by": "fcarraldo", "context": "Team on a greenfield project, no affiliation", "url": "https://news.ycombinator.com/item?id=49494042", "date": "2026-08-29"}, {"by": "etoxin", "context": "works on a team", "url": "https://news.ycombinator.com/item?id=48548395", "date": "2026-06-15"}], "tags": ["for spec-driven development", "for teams", "CLI tool", "for brownfield projects", "for regulated work"], "use_cases": ["spec-driven development", "spec-driven ai development", "spec-driven agent development", "spec-driven ai coding workflow", "spec-driven agent changes", "spec-driven development with ai agents"], "compared": [{"slug": "superpowers", "name": "Superpowers", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "gsd", "name": "GSD", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49734264", "title": "OpenSpec \u2013 A lightweight and configurable AI spec framework", "mentions": 8}, {"url": "https://news.ycombinator.com/item?id=50100387", "title": "Aidlc: Adaptive workflow steering rules for AI coding agents", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50063427", "title": "AI is a tool and using it well takes skill", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50025182", "title": "We Are Not All Terrible Developers", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49710015", "title": "How much of F-Droid is LLM generated?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49648732", "title": "Creativity is the new moat", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {"recommend": 1}, "2026-05": {"neutral": 1}, "2026-06": {"neutral": 1}, "2026-07": {"recommend": 1}, "2026-08": {"recommend": 3, "neutral": 1}, "2026-09": {"recommend": 5, "warn": 1, "neutral": 2, "compare": 1}, "2026-10": {"recommend": 2}}, "quotes": [{"id": 801642032, "item_id": 50102627, "url": "https://news.ycombinator.com/item?id=50102627", "by": "daitangio", "date": "2026-10-15", "stance": "recommend", "quote": "I prefer https://github.com/Fission-AI/OpenSpec because it works also on brown-field.", "excerpt": "I prefer https://github.com/Fission-AI/OpenSpec because it works also on brown-field. If you want an unbias-demo, take a look also at https://github.com/daitangio/take-ai-control/tree/demo/nello-openspec branch demo/nello-openspec", "context": "", "use_case": "spec-driven AI coding workflow", "switched_from": "", "story": "Aidlc: Adaptive workflow steering rules for AI coding agents"}, {"id": 801385520, "item_id": 50086595, "url": "https://news.ycombinator.com/item?id=50086595", "by": "Zambyte", "date": "2026-10-14", "stance": "recommend", "quote": "I use something similar (openspec change specifications rather than a literal ROADMAP.md file)", "excerpt": "I use something similar (openspec change specifications rather than a literal ROADMAP.md file) and I will sometimes spend hours iterating on the details of a change file, before letting my agent actually implement it. Yes, the agent is generally dealing with doing the actual editing, but I will read it and use dictation to direct modifications to the file.", "context": "", "use_case": "spec-driven agent changes", "switched_from": "", "story": "AI is a tool and using it well takes skill"}, {"id": 800405904, "item_id": 50025369, "url": "https://news.ycombinator.com/item?id=50025369", "by": "Zambyte", "date": "2026-10-09", "stance": "recommend", "quote": "I use a tool called openspec to drive the framework of creating proposal, design, and task documents, ahead of driving the implementation.", "excerpt": "> Otherwise it\u2019s all a black box. You ask for something, code comes out, and you hope it does what you meant. It's easy to argue against the worst example of something. Using AI to program can be done well, or it can be done poorly. Using compilers and interpreters to program can be done well or poorly as well. There is nothing fundamental about AI programming that limits programmer comprehension, care, or influence ", "context": "", "use_case": "spec-driven development with AI agents", "switched_from": "", "story": "We Are Not All Terrible Developers"}, {"id": 795873504, "item_id": 49742094, "url": "https://news.ycombinator.com/item?id=49742094", "by": "_blk", "date": "2026-09-17", "stance": "compare", "quote": "How does it compare to GSD (opengsd.net)? Just from the command set it seems a lot lighter but also less expressive.", "excerpt": "Interesting project. How does it compare to GSD (opengsd.net)? Just from the command set it seems a lot lighter but also less expressive. GSD is quite OK but very token hungry (~4x but it buys traceability and has quite a powerful autonomous mode) I use gsd-meta-manager to manage multiple GSD projects in parallel without having to use a skill to query each project individually to see where they're at. Does openspec h", "context": "", "use_case": "AI spec framework", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795822992, "item_id": 49738937, "url": "https://news.ycombinator.com/item?id=49738937", "by": "mafro", "date": "2026-09-17", "stance": "neutral", "quote": "What I did find very useful and have retained is the process flow.", "excerpt": "I've used OpenSpec extensively on two large pieces of software which were worked solo over 6-9 months. Recently, I've completely ditched the specification part. I found they just weren't useful over the longer term. I used an LLM to assess in both directions whether the code matched the specs and whether the specs matched the code. On both software projects this came out with huge divergence from spec to code. Basica", "context": "solo developer on two large projects", "use_case": "spec-driven development with LLM", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795788848, "item_id": 49736803, "url": "https://news.ycombinator.com/item?id=49736803", "by": "jochem9", "date": "2026-09-17", "stance": "recommend", "quote": "The power is that you do a lot of upfront thinking.", "excerpt": "I use it at a much smaller scale. I think that's also the right place, because its a CLI tool + skills that generate md files. Not something you'd give to a business person. I start from a single ticket (sometimes just a handful of changes, but I want the spec as docs) to changes that you'd normally split over several tickets. Basically the flow proposal -> design -> specs -> tasks gives you and AI a method to build ", "context": "uses it on a small team with PR review", "use_case": "spec-driven AI development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795768384, "item_id": 49735524, "url": "https://news.ycombinator.com/item?id=49735524", "by": "recroad", "date": "2026-09-17", "stance": "recommend", "quote": "I use this to produce the task list which I then feed into a Ralph loop using a bash script.", "excerpt": "I use this to produce the task list which I then feed into a Ralph loop using a bash script. I save a lot of tokens since each tasks context is so small.", "context": "", "use_case": "producing task lists for agent loop", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795767952, "item_id": 49735497, "url": "https://news.ycombinator.com/item?id=49735497", "by": "alexjplant", "date": "2026-09-17", "stance": "recommend", "quote": "Using OpenSpec keeps things as constrained as possible with the side effect of recording what your system does.", "excerpt": "I bother because Claude Code does wacky nonsense unless I use OpenSpec (or something similar) to explicitly research, scope, persist, then implement in a brand-new context. Even Opus will do ridiculous nonsense like throw its hands up when asked to start a Docker container, ignore explicit architectural instructions, write verbose make-work documentation riddled with inaccuracies, etc. Using OpenSpec keeps things as ", "context": "constrained by regulations at day job", "use_case": "constraining coding agents", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795759424, "item_id": 49734964, "url": "https://news.ycombinator.com/item?id=49734964", "by": "honkycat", "date": "2026-09-17", "stance": "recommend", "quote": "Easily my favorite spec driven development framework.", "excerpt": "LOVE. LOVE. LOVE. Openspec. Easily my favorite spec driven development framework. It scored really well in our internal evals as well. I think it has the most sane ceremony and its model fits my mental model really well. I've also been working on a TUI that will automatically generate \"phases\" with each one being a openspec spec. I would highly recommend trying out SpecDriven development. I found it to be the most pr", "context": "", "use_case": "spec-driven development with LLMs", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795754497, "item_id": 49734656, "url": "https://news.ycombinator.com/item?id=49734656", "by": "wyum", "date": "2026-09-16", "stance": "neutral", "quote": "it seems to share a similar philosophy to what I've been working on this year.", "excerpt": "This is my first time seeing openspec, and it seems to share a similar philosophy to what I've been working on this year. If you like this / SDD, I'd appreciate your feedback: https://github.com/spekk-ai/spekk-cli Similar iterative specs philosophy. Ours is a bit different because we focus on declarative specs and installable agent skills. We chose Go for simplicity and minimal requirements (single binary).", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795753488, "item_id": 49734593, "url": "https://news.ycombinator.com/item?id=49734593", "by": "CharlieDigital", "date": "2026-09-16", "stance": "warn", "quote": "Somehow not very confidence inspiring...", "excerpt": "This section https://openspec.dev/docs/setup links to \"Concepts\" Concepts links here: https://github.com/Fission-AI/OpenSpec/blob/main/docs-lab/guides/concepts.md All the docs here are the templates rather than the actual file (I presume: https://github.com/Fission-AI/OpenSpec/blob/main/docs/concepts.md) Somehow not very confidence inspiring...", "context": "", "use_case": "", "switched_from": "", "story": "OpenSpec \u2013 A lightweight and configurable AI spec framework"}, {"id": 795379681, "item_id": 49711230, "url": "https://news.ycombinator.com/item?id=49711230", "by": "Zambyte", "date": "2026-09-15", "stance": "recommend", "quote": "Writing good specifications is the key detail here.", "excerpt": "Up until the last couple of months, I have treated LLMs as a supercharged stackoverflow. I would ask it questions on how to do something in a general sense, and then adapt the answer to my use case. Now, my entire programming flow does not even include an editor. The tools I use are: pi.dev to write and implement openspec specifications, herdr to manage many pi instances, and ollama to run qwen 3.8 27b on my single 7", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "How much of F-Droid is LLM generated?"}, {"id": 794395776, "item_id": 49649736, "url": "https://news.ycombinator.com/item?id=49649736", "by": "Zambyte", "date": "2026-09-10", "stance": "recommend", "quote": "I personally use the tool openspec, and I like it because it explicitly captures my reasoning in the documents it produces", "excerpt": "I like to think of it as a how -> what -> why pipeline. Early programming in assembly mostly involved telling the computer how to do things that you want it to do. You instruct it in terms of the mechanical capabilities of the machine. Compilers and interpreters came along and raised the layer of abstraction that programmers work on from the \"how\" domain to the \"what\" domain. Instead of saying how to move bits around", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Creativity is the new moat"}, {"id": 793305440, "item_id": 49581590, "url": "https://news.ycombinator.com/item?id=49581590", "by": "Zambyte", "date": "2026-09-05", "stance": "recommend", "quote": "I have found using openspec (no affiliation, just enjoy the tool) to be useful", "excerpt": "AI is great for offloading problems that you don't want to solve, but you want done. The key is finding what problems you find important to solve yourself. At this point, roughly all the code I push is generated by AI. I find the code itself to be mostly an implementation detail of what I'm trying to do. However, I do not trust AI to write sustainable software that I can easily extend in ways that I know the project ", "context": "", "use_case": "spec-driven AI development", "switched_from": "", "story": "Is AI ruining my brain?"}, {"id": 792127187, "item_id": 49507949, "url": "https://news.ycombinator.com/item?id=49507949", "by": "mstaoru", "date": "2026-08-31", "stance": "neutral", "quote": "I experiment with different plan-build-evaluate frameworks like GSD, OpenSpec, Superpowers.", "excerpt": "It is very difficult. I consider myself reasonably skilled in AI usage (multiple harnesses, skills, MCP, etc). I use only the latest models: Opus 5, GPT 5.6 Sol. I experiment with different plan-build-evaluate frameworks like GSD, OpenSpec, Superpowers. I have a reasonable AGENTS.md without much cruft: test coverage ~80%, ASD-STE100 English, use uv - things like that. I can churn out single-use scripts and micro-proj", "context": "", "use_case": "plan-build-evaluate workflows", "switched_from": "", "story": "Why do I lose my passion and want to do nothing?"}, {"id": 791988688, "item_id": 49499293, "url": "https://news.ycombinator.com/item?id=49499293", "by": "alasano", "date": "2026-08-30", "stance": "recommend", "quote": "I use and love openspec", "excerpt": "I use and love openspec and I'm against this session attribution by default setting. But I do see the value in seeing the conversation that lead to the spec. I make sure that all product decisions go through me prior to the agent writing the spec and the questions I ask and decisions I make could definitely help understand retroactively why something is the way it is. I guess with the default openspec schema you woul", "context": "", "use_case": "spec-driven agent development", "switched_from": "", "story": "Claude Session URL appended to commit messages and PR descriptions by default"}, {"id": 791904672, "item_id": 49494042, "url": "https://news.ycombinator.com/item?id=49494042", "by": "fcarraldo", "date": "2026-08-29", "stance": "recommend", "quote": "we all agreed to use OpenSpec early on, and to commit the specs alongside the code", "excerpt": "I\u2019ve had a good experience with a greenfield project. The single thing that seems to have helped is that we all agreed to use OpenSpec early on, and to commit the specs alongside the code. I have no affiliation with OpenSpec and I don\u2019t suspect it\u2019s doing anything unique here, but having the intent develop alongside the code in the repository seems to have ensured that agents have a more holistic view of the project.", "context": "Team on a greenfield project, no affiliation", "use_case": "spec-driven agent development", "switched_from": "", "story": "Domain-Driven Agents"}, {"id": 788999152, "item_id": 49312447, "url": "https://news.ycombinator.com/item?id=49312447", "by": "guilyguily", "date": "2026-08-15", "stance": "recommend", "quote": "I use openspec in addition with the /grill-me skill and it really helps clearing the path before starting to code.", "excerpt": "I use openspec in addition with the /grill-me skill and it really helps clearing the path before starting to code. I think the goal of engineering, when using AI, is to maximize your value upfront instead of every five minutes.", "context": "", "use_case": "spec-driven AI coding", "switched_from": "", "story": "The AI Situation in Software Development"}, {"id": 785458544, "item_id": 49091159, "url": "https://news.ycombinator.com/item?id=49091159", "by": "LiveTheDream", "date": "2026-07-28", "stance": "recommend", "quote": "You should take a look at OpenSpec[0]. It implements your points 1-3.", "excerpt": "You should take a look at OpenSpec[0]. It implements your points 1-3. [0] https://openspec.dev/", "context": "", "use_case": "agent plan management", "switched_from": "", "story": "Benchmarking Opus 5 on SlopCodeBench"}, {"id": 776774320, "item_id": 48548395, "url": "https://news.ycombinator.com/item?id=48548395", "by": "etoxin", "date": "2026-06-15", "stance": "neutral", "quote": "We use openspec with our projects at work.", "excerpt": "I have not. We use openspec with our projects at work. To try and simulate a local rig without spending big cash. I use the hosted models and pay for them with the latest popular local model. Most small local models don't get tool calling right, however the larger models are now doing this correctly now. One thing local has not accounted for, is most productive engineers are running multiple cli chats at a time with ", "context": "works on a team", "use_case": "spec-driven development", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 767910928, "item_id": 47994433, "url": "https://news.ycombinator.com/item?id=47994433", "by": "arikrahman", "date": "2026-05-03", "stance": "neutral", "quote": "I use OpenSpec for my spec management", "excerpt": "I use OpenSpec for my spec management, and I scrolled down to the comparison. The gripe seems to be with a semantic difference. Specs describing a current system is the basis for AS/IS Gap Analysis. Also, I mainly pursue these tools so that I can have AI accelerate this process and broker an agreement after negotiating specs with the agent.", "context": "", "use_case": "spec management for AI coding", "switched_from": "", "story": "Specsmaxxing \u2013 On overcoming AI psychosis, and why I write specs in YAML"}, {"id": 766356961, "item_id": 47897310, "url": "https://news.ycombinator.com/item?id=47897310", "by": "arikrahman", "date": "2026-04-24", "stance": "recommend", "quote": "using Open Spec to negotiate requirements before the handoff, has helped me a lot", "excerpt": "I use Aider nowadays, and will probably cancel my Github multi AI bundle subscription due to the new training policy. I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "context": "", "use_case": "negotiating requirements before coding", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}, {"id": 758712624, "item_id": 47419539, "url": "https://news.ycombinator.com/item?id=47419539", "by": "recroad", "date": "2026-03-17", "stance": "recommend", "quote": "I used openspec and love it.", "excerpt": "I used openspec and love it. https://zarar.dev/spec-driven-development-from-vibe-coding-to-structured-development/", "context": "", "use_case": "spec-driven development", "switched_from": "", "story": "Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System"}]}