{"slug": "roborev", "name": "roborev", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 4, "commenters": 5, "warners": 0, "score": 3.737, "rising": -1.31, "first": "2026-02-12", "latest": "2026-06-08", "why": "One nice example that applies this quite nicely is roborev", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 1, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 2, 1, 0, 0, 1, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "One nice example that applies this quite nicely is roborev", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/roborev-dev/roborev", "official_url": "https://github.com/roborev-dev/roborev", "pricing": "", "aliases": ["roborev"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 775089136, "item_id": 48443071, "url": "https://news.ycombinator.com/item?id=48443071", "by": "nicolailolansen", "date": "2026-06-08", "version": null, "stance": "recommend", "quote": "git or coding review loops ( i use roborev )", "excerpt": "Yeah. It's very easy to give a definitive \"yes\", if you've ever worked with coding agents in any capacity. I use them in much the same way as you, there are a bunch of things that would be nice for the agent to know, specifically for me, the project, or how I would like it to run as an example: git or coding review loops ( i use roborev ). Asking the agent to do these things every time, is very time consuming.", "context": "", "use_case": "coding agent review loops", "switched_from": "", "story": "Do agents.md files help coding agents?"}, {"id": 755359638, "item_id": 47209977, "url": "https://news.ycombinator.com/item?id=47209977", "by": "wenc", "date": "2026-03-01", "version": null, "stance": "recommend", "quote": "`roborev` (Wes McKinney) to do automatic code reviews and fixes.", "excerpt": "MCPs (especially remote MCPs) are like a black box API -- you don't have to install anything, provision any resources, etc. You just call it and get an answer. There's a place for that, but an MCP is ultimately a blunt instrument. CLI tools on the other hand are like precision instruments. Yes, you have to install them locally once, but after that, they have access to your local environment and can discover things on", "context": "ML work with agents", "use_case": "automatic code review", "switched_from": "", "story": "MCP is dead. Long live the CLI"}, {"id": 754343361, "item_id": 47146460, "url": "https://news.ycombinator.com/item?id=47146460", "by": "onecommit", "date": "2026-02-24", "version": null, "stance": "recommend", "quote": "is moving in the right direction", "excerpt": "Thanks! What tools have you been experimenting with? Agreed. That this evolution pushes much of the work into describing desired outcomes and giving sufficient context. To your questions: Emdash helps reduce the setup cost of each environment by allowing you to open an isolated git worktree, copying over env variables and other desired context. And then preserving your conversation per task. That said, you still need", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Emdash \u2013 Open-source agentic development environment"}, {"id": 751961184, "item_id": 46997574, "url": "https://news.ycombinator.com/item?id=46997574", "by": "thenaturalist", "date": "2026-02-12", "version": null, "stance": "recommend", "quote": "One nice example that applies this quite nicely is roborev", "excerpt": "Adverserial work (be it agent or human). The one difference between \"can do\" and \"should be trusted to do\" is the ability to systematically prove that \"can do\" holds up close to 100% of task instances and under adverserial conditions. Hacking and pentesting are already scaling fully autonomously - and systematically. For now, lower level targets aren't yet attractive as such scale requires sophisticated (state) actor", "context": "", "use_case": "", "switched_from": "", "story": "What happens when capability decouples from credentials?"}]}], "caveats": [], "who": [{"by": "wenc", "context": "ML work with agents", "url": "https://news.ycombinator.com/item?id=47209977", "date": "2026-03-01"}], "tags": [], "use_cases": ["coding agent review loops", "automatic code review"], "compared": [], "makers": [{"id": 750955712, "item_id": 46934732, "url": "https://news.ycombinator.com/item?id=46934732", "by": "wesm", "date": "2026-02-08", "version": null, "stance": "neutral", "quote": "I've been building https://roborev.io/ (continuous background code review for agents)", "excerpt": "I've been building https://roborev.io/ (continuous background code review for agents) essentially as a cope to supervise the poor quality of the agents' work, since my agents write much more code than I can possible review directly or QA thoroughly. I think we'll see a bunch of interesting new tools to help alleviate the cognitive burden of supervising their work output.", "context": "", "use_case": "background code review for agents", "switched_from": "", "story": "AI fatigue Is real and nobody talks about it"}], "threads": [{"url": "https://news.ycombinator.com/item?id=48441589", "title": "Do agents.md files help coding agents?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47828968", "title": "Show HN: A lightweight way to make agents talk without paying for API usage", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47208398", "title": "MCP is dead. Long live the CLI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47140322", "title": "Show HN: Emdash \u2013 Open-source agentic development environment", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46997470", "title": "What happens when capability decouples from credentials?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46934404", "title": "AI fatigue Is real and nobody talks about it", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"recommend": 2}, "2026-03": {"recommend": 1}, "2026-04": {"neutral": 1}, "2026-05": {}, "2026-06": {"recommend": 1}, "2026-07": {}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 775089136, "item_id": 48443071, "url": "https://news.ycombinator.com/item?id=48443071", "by": "nicolailolansen", "date": "2026-06-08", "version": null, "stance": "recommend", "quote": "git or coding review loops ( i use roborev )", "excerpt": "Yeah. It's very easy to give a definitive \"yes\", if you've ever worked with coding agents in any capacity. I use them in much the same way as you, there are a bunch of things that would be nice for the agent to know, specifically for me, the project, or how I would like it to run as an example: git or coding review loops ( i use roborev ). Asking the agent to do these things every time, is very time consuming.", "context": "", "use_case": "coding agent review loops", "switched_from": "", "story": "Do agents.md files help coding agents?"}, {"id": 765275616, "item_id": 47829726, "url": "https://news.ycombinator.com/item?id=47829726", "by": "scalefirst", "date": "2026-04-19", "version": null, "stance": "neutral", "quote": "Have you seen https://www.roborev.io/ from Wes McKinney?", "excerpt": "Have you seen https://www.roborev.io/ from Wes McKinney?", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: A lightweight way to make agents talk without paying for API usage"}, {"id": 755359638, "item_id": 47209977, "url": "https://news.ycombinator.com/item?id=47209977", "by": "wenc", "date": "2026-03-01", "version": null, "stance": "recommend", "quote": "`roborev` (Wes McKinney) to do automatic code reviews and fixes.", "excerpt": "MCPs (especially remote MCPs) are like a black box API -- you don't have to install anything, provision any resources, etc. You just call it and get an answer. There's a place for that, but an MCP is ultimately a blunt instrument. CLI tools on the other hand are like precision instruments. Yes, you have to install them locally once, but after that, they have access to your local environment and can discover things on", "context": "ML work with agents", "use_case": "automatic code review", "switched_from": "", "story": "MCP is dead. Long live the CLI"}, {"id": 754343361, "item_id": 47146460, "url": "https://news.ycombinator.com/item?id=47146460", "by": "onecommit", "date": "2026-02-24", "version": null, "stance": "recommend", "quote": "is moving in the right direction", "excerpt": "Thanks! What tools have you been experimenting with? Agreed. That this evolution pushes much of the work into describing desired outcomes and giving sufficient context. To your questions: Emdash helps reduce the setup cost of each environment by allowing you to open an isolated git worktree, copying over env variables and other desired context. And then preserving your conversation per task. That said, you still need", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Emdash \u2013 Open-source agentic development environment"}, {"id": 751961184, "item_id": 46997574, "url": "https://news.ycombinator.com/item?id=46997574", "by": "thenaturalist", "date": "2026-02-12", "version": null, "stance": "recommend", "quote": "One nice example that applies this quite nicely is roborev", "excerpt": "Adverserial work (be it agent or human). The one difference between \"can do\" and \"should be trusted to do\" is the ability to systematically prove that \"can do\" holds up close to 100% of task instances and under adverserial conditions. Hacking and pentesting are already scaling fully autonomously - and systematically. For now, lower level targets aren't yet attractive as such scale requires sophisticated (state) actor", "context": "", "use_case": "", "switched_from": "", "story": "What happens when capability decouples from credentials?"}]}