{"slug": "forge", "name": "Forge", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 5, "warners": 0, "score": 3.249, "rising": -0.98, "first": "2026-01-04", "latest": "2026-07-28", "why": "I now use Forge to plan css too because I don't want to show broken css states", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 2, "compare": 0, "warn": 0}, "spark": [0, 0, 1, 0, 1, 0, 0, 2, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I now use Forge to plan css too because I don't want to show broken css states", "icon": true, "domain": null, "github_repo": "github.com/card-forge/forge", "official_url": "https://github.com/card-forge/forge", "pricing": "", "aliases": ["Forge", "forge"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 777315680, "item_id": 48582230, "url": "https://news.ycombinator.com/item?id=48582230", "by": "3abiton", "date": "2026-06-18", "stance": "recommend", "quote": "I use forge, and I have been inpressed with what it can do given all the limitations of local models.", "excerpt": "And a big thing that's missing is ... the harness comparison. Ot plays a very big role. I use forge, and I have been inpressed with what it can do given all the limitations of local models.", "context": "", "use_case": "harness for local models", "switched_from": "", "story": "Local Qwen isn't a worse Opus, it's a different tool"}, {"id": 775077920, "item_id": 48442370, "url": "https://news.ycombinator.com/item?id=48442370", "by": "mullingitover", "date": "2026-06-08", "stance": "recommend", "quote": "I'm guessing it's going to be an absolute banger of a month for forge[1] and the like.", "excerpt": "I'm guessing it's going to be an absolute banger of a month for forge[1] and the like. [1] https://github.com/antoinezambelli/forge", "context": "", "use_case": "", "switched_from": "", "story": "Is This the Dawn of the Tokenpocalypse?"}, {"id": 757169312, "item_id": 47323082, "url": "https://news.ycombinator.com/item?id=47323082", "by": "hackermailman", "date": "2026-03-10", "stance": "recommend", "quote": "I now use Forge to plan css too because I don't want to show broken css states", "excerpt": "This is how you get to 10x with a LLM in my limited agentic experience for doing all the scratchwork of architecting a program before you generate it: The user facing part of your program can be planned out using conceptual design https://essenceofsoftware.com/tutorials/ the author of that book teaches it in MITs old software studio course https://61040-fa25.github.io/schedule the point is to plan out modularity and ", "context": "limited agentic coding experience", "use_case": "formal modeling before generating code", "switched_from": "", "story": "Ask HN: Are we going to see more job postings asking for only agentic coding?"}, {"id": 743893520, "item_id": 46493345, "url": "https://news.ycombinator.com/item?id=46493345", "by": "hackermailman", "date": "2026-01-04", "stance": "recommend", "quote": "\"Lightweight formal methods\" meaning you build a model of some program logic and test it's properties hold.", "excerpt": "\"Lightweight formal methods\" meaning you build a model of some program logic and test it's properties hold. https://forge-fm.github.io/book/ Beyond that is dependent types", "context": "", "use_case": "lightweight formal methods modeling", "switched_from": "", "story": "Ask HN: What's the future of software testing and QA?"}]}], "caveats": [], "who": [{"by": "hackermailman", "context": "limited agentic coding experience", "url": "https://news.ycombinator.com/item?id=47323082", "date": "2026-03-10"}], "tags": [], "use_cases": ["tiling window management", "harness for local models", "rules engine for mtg llm play", "formal modeling before generating code", "lightweight formal methods modeling"], "compared": [], "makers": [{"id": 748850544, "item_id": 46803159, "url": "https://news.ycombinator.com/item?id=46803159", "by": "brady_bastian", "date": "2026-01-28", "stance": "recommend", "quote": "I built Forge to solve this.", "excerpt": "Hi HN, I\u2019m Brady. I\u2019ve spent years watching data engineers burn out writing brittle parsers for nested JSON, only to have dashboards crash because an upstream API changed a field name. I built Forge to solve this. It\u2019s an autonomous data infrastructure platform that ingests raw, nested JSON and automatically generates production-ready dbt models. The Problem Traditional ETL tools (Fivetran/Stitch) often dump raw JSON", "context": "", "use_case": "turning nested JSON into dbt models", "switched_from": "", "story": "Forge \u2013 Transform nested JSON into governed dbt models for BQ/Snowflake"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49090607", "title": "Show HN: I was tired of opening 2 tabs for every HN link, so I made a userscript", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48580209", "title": "Local Qwen isn't a worse Opus, it's a different tool", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48492177", "title": "MTG Bench: Testing how well LLMs can play magic", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48442136", "title": "Is This the Dawn of the Tokenpocalypse?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47303745", "title": "Ask HN: Are we going to see more job postings asking for only agentic coding?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46803158", "title": "Forge \u2013 Transform nested JSON into governed dbt models for BQ/Snowflake", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 2, "neutral": 1}, "2026-07": {"neutral": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 785483872, "item_id": 49092742, "url": "https://news.ycombinator.com/item?id=49092742", "by": "kccqzy", "date": "2026-07-28", "stance": "neutral", "quote": "I'm currently using Forge (https://github.com/forge-ext/forge) but sadly it's becoming unmaintained.", "excerpt": "Feature 2 is really useful. When I land on a technical article I know chances are there will be a nice HN discussion, that may sometimes even refute the main point of the article. Feature 1 is IMO less useful. It just suggests that people are bad at window management. We didn't like overlapping windows and finding them, so we created tabs inside windows. Then we wanted to see two things at the same time, so we create", "context": "", "use_case": "tiling window management", "switched_from": "", "story": "Show HN: I was tired of opening 2 tabs for every HN link, so I made a userscript"}, {"id": 777315680, "item_id": 48582230, "url": "https://news.ycombinator.com/item?id=48582230", "by": "3abiton", "date": "2026-06-18", "stance": "recommend", "quote": "I use forge, and I have been inpressed with what it can do given all the limitations of local models.", "excerpt": "And a big thing that's missing is ... the harness comparison. Ot plays a very big role. I use forge, and I have been inpressed with what it can do given all the limitations of local models.", "context": "", "use_case": "harness for local models", "switched_from": "", "story": "Local Qwen isn't a worse Opus, it's a different tool"}, {"id": 775973568, "item_id": 48498348, "url": "https://news.ycombinator.com/item?id=48498348", "by": "josh_p", "date": "2026-06-11", "stance": "neutral", "quote": "I do still wonder if adapting something like card forge for llm use would result in engaging gameplay with an llm.", "excerpt": "I know the author specifically did not use a rules engine in their simulation because of uncertainty on how it would affect it. I do still wonder if adapting something like card forge for llm use would result in engaging gameplay with an llm. https://github.com/Card-Forge/forge", "context": "", "use_case": "rules engine for MTG LLM play", "switched_from": "", "story": "MTG Bench: Testing how well LLMs can play magic"}, {"id": 775077920, "item_id": 48442370, "url": "https://news.ycombinator.com/item?id=48442370", "by": "mullingitover", "date": "2026-06-08", "stance": "recommend", "quote": "I'm guessing it's going to be an absolute banger of a month for forge[1] and the like.", "excerpt": "I'm guessing it's going to be an absolute banger of a month for forge[1] and the like. [1] https://github.com/antoinezambelli/forge", "context": "", "use_case": "", "switched_from": "", "story": "Is This the Dawn of the Tokenpocalypse?"}, {"id": 757169312, "item_id": 47323082, "url": "https://news.ycombinator.com/item?id=47323082", "by": "hackermailman", "date": "2026-03-10", "stance": "recommend", "quote": "I now use Forge to plan css too because I don't want to show broken css states", "excerpt": "This is how you get to 10x with a LLM in my limited agentic experience for doing all the scratchwork of architecting a program before you generate it: The user facing part of your program can be planned out using conceptual design https://essenceofsoftware.com/tutorials/ the author of that book teaches it in MITs old software studio course https://61040-fa25.github.io/schedule the point is to plan out modularity and ", "context": "limited agentic coding experience", "use_case": "formal modeling before generating code", "switched_from": "", "story": "Ask HN: Are we going to see more job postings asking for only agentic coding?"}, {"id": 743893520, "item_id": 46493345, "url": "https://news.ycombinator.com/item?id=46493345", "by": "hackermailman", "date": "2026-01-04", "stance": "recommend", "quote": "\"Lightweight formal methods\" meaning you build a model of some program logic and test it's properties hold.", "excerpt": "\"Lightweight formal methods\" meaning you build a model of some program logic and test it's properties hold. https://forge-fm.github.io/book/ Beyond that is dependent types", "context": "", "use_case": "lightweight formal methods modeling", "switched_from": "", "story": "Ask HN: What's the future of software testing and QA?"}]}