{"slug": "coderabbit", "name": "CodeRabbit", "category": "ai", "category_name": "AI models and assistants", "description": "AI code review tool that automatically comments on pull requests and merge requests.", "recommenders": 8, "commenters": 19, "warners": 3, "score": 6.649, "rising": 1.36, "first": "2025-11-21", "latest": "2026-10-17", "why": "Commenters use it as an automated pull-request reviewer that catches real issues, looks at code beyond the diff and costs a flat per-developer price.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 8, "neutral": 8, "compare": 1, "warn": 3}, "spark": [1, 1, 0, 0, 0, 0, 0, 3, 0, 2, 0, 1], "listed": true, "loved": ["Catches issues", "PR integration"], "caveat": "Missed bugs", "short_quote": "We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it.", "icon": true, "domain": "coderabbit.ai", "github_repo": null, "official_url": "https://www.coderabbit.ai/", "pricing": "freemium", "aliases": ["CodeRabbit"], "verdict": [{"text": "Commenters use it as an automated pull-request reviewer that catches real issues", "cites": [{"id": 788796768, "item_id": 49299798, "url": "https://news.ycombinator.com/item?id=49299798", "by": "ryanchants", "date": "2026-08-14", "stance": "recommend", "quote": "We use CodeRabbit at work, which catches good stuff.", "excerpt": "Increasingly not. We use CodeRabbit at work, which catches good stuff. And I have my own gauntlet that I run code through. https://github.com/jacquardlabs/gauntlet", "context": "", "use_case": "automated code review", "switched_from": "", "story": "Ask HN: Does a human still review your code?"}, {"id": 774512208, "item_id": 48407013, "url": "https://news.ycombinator.com/item?id=48407013", "by": "atestu", "date": "2026-06-04", "stance": "recommend", "quote": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.", "excerpt": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot. I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed. Coderabbit just came out with their own PR review UI that's great for big PRs, it groups files together etc. https://www.coderabbit.ai/blog/introducing-atlas-the-first-ai-native", "context": "", "use_case": "AI pull request review", "switched_from": "", "story": "Alibaba/Open-Code-Review"}, {"id": 736183104, "item_id": 46011444, "url": "https://news.ycombinator.com/item?id=46011444", "by": "bebop", "date": "2025-11-21", "stance": "recommend", "quote": "We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it.", "excerpt": "We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it. Might be worth a look. Not affiliated in any way.", "context": "", "use_case": "automated code reviews", "switched_from": "", "story": "Command Lines"}, {"id": 777548032, "item_id": 48596752, "url": "https://news.ycombinator.com/item?id=48596752", "by": "jcubic", "date": "2026-06-19", "stance": "recommend", "quote": "I mostly use CodeRabbit via GitHub PR", "excerpt": "I mostly use CodeRabbit via GitHub PR https://www.coderabbit.ai/", "context": "", "use_case": "AI code review", "switched_from": "", "story": "Ask HN: What tools are you using for AI-assisted code review?"}]}, {"text": ", looks at code beyond the diff", "cites": [{"id": 741573312, "item_id": 46348332, "url": "https://news.ycombinator.com/item?id=46348332", "by": "howToTestFE", "date": "2025-12-21", "stance": "recommend", "quote": "i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff", "excerpt": "while this approach is useful, i think the diff is too small to catch a lot of bugs. i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff, and definitely can see the rest of the file your are editing (not just the lines in the diff)", "context": "", "use_case": "AI code review", "switched_from": "", "story": "Get an AI code review in 10 seconds"}]}, {"text": " and costs a flat per-developer price.", "cites": [{"id": 774512208, "item_id": 48407013, "url": "https://news.ycombinator.com/item?id=48407013", "by": "atestu", "date": "2026-06-04", "stance": "recommend", "quote": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.", "excerpt": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot. I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed. Coderabbit just came out with their own PR review UI that's great for big PRs, it groups files together etc. https://www.coderabbit.ai/blog/introducing-atlas-the-first-ai-native", "context": "", "use_case": "AI pull request review", "switched_from": "", "story": "Alibaba/Open-Code-Review"}]}, {"text": " The most common complaints are shallow or noisy feedback", "cites": [{"id": 789583408, "item_id": 49348963, "url": "https://news.ycombinator.com/item?id=49348963", "by": "crabbone", "date": "2026-08-18", "stance": "neutral", "quote": "I used CodeRabbit at work, and I have mixed feelings about it.", "excerpt": "1. I'm not sure what CodeRabbit has to do with the article... It's obviously an advertisement, but it's merged into the text of the article, which I find bizarre. As an aside, I used CodeRabbit at work, and I have mixed feelings about it. I'm not entirely against using it or a similar tool, but people often treat the comments from CodeRabbit as a gospel, and they can harm their code as a result. Also, I've never seen", "context": "", "use_case": "code review", "switched_from": "", "story": "Kent Beck: Composable Tests"}, {"id": 779973616, "item_id": 48748351, "url": "https://news.ycombinator.com/item?id=48748351", "by": "anee769", "date": "2026-07-01", "stance": "warn", "quote": "we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so eventually we stopped relying on it.", "excerpt": "The hardest part of review tools like this is signal-to-noise \u2014 one round of false positives and people start reflex-accepting or muting it. How does Ox decide what's worth flagging on a given PR, and does it dedupe against pre-existing debt so it only surfaces what the change actually introduced? In my company, we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so e", "context": "uses it at their company", "use_case": "AI code review", "switched_from": "", "story": "Show HN: Ox \u2013 an AI agent that catches tech debt before it's committed"}, {"id": 797998416, "item_id": 49874901, "url": "https://news.ycombinator.com/item?id=49874901", "by": "quatotor", "date": "2026-09-28", "stance": "warn", "quote": "I have similar experience with coderabbit we use at work.", "excerpt": "I have similar experience with coderabbit we use at work. On the other hand codex with astra I use locally is way better. Still AI review is very different from human review. AI is better in paying attention and in finding bugs but it is incapable to detect code smells, wrong architectural decisions or domain errors. Although AI is still way better in code reviews than in writing code. It make sense to use it as anot", "context": "", "use_case": "AI code review", "switched_from": "", "story": "There is more to code review than (automatable) detection"}]}, {"text": " and bugs it misses that other reviewers catch.", "cites": [{"id": 795263489, "item_id": 49703968, "url": "https://news.ycombinator.com/item?id=49703968", "by": "dlahoda", "date": "2026-09-14", "stance": "compare", "quote": "finds bugs missed by coderabitai, devin-integration-bot, codex and copilot", "excerpt": "I would and do. works perfect https://github.com/dzmitry-lahoda/dz/tree/main/agents/skills/code-review burns half of day sub of astra for 200 USD. runs 1 hour on our repo. finds bugs missed by coderabitai, devin-integration-bot, codex and copilot (I ask them first until nothing found, yet my orchestration finds more). I do not hardcode our application in orchestration, but run subagent for applicationdomainproduct de", "context": "", "use_case": "PR code review", "switched_from": "", "story": "GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?"}, {"id": 792298946, "item_id": 49518684, "url": "https://news.ycombinator.com/item?id=49518684", "by": "eskibars", "date": "2026-09-01", "stance": "neutral", "quote": "no problem with CodeRabbit", "excerpt": "Author here. I built ZeroQuarry, and I was considering deploying an open source link shortener or using a SaaS one. I googled around and then found iShortn, so ran the iShortn scan with it. I found a bunch of vulnerabilities, which I sent to the maintainer and have now been patched, but some of the most interesting ones I found were that many of these vulnerabilities were actually crafted by (or at least reviewed by)", "context": "", "use_case": "AI code review", "switched_from": "", "story": "What AI code review misses: SSRF and more"}, {"id": 750288944, "item_id": 46893059, "url": "https://news.ycombinator.com/item?id=46893059", "by": "kachapopopow", "date": "2026-02-04", "stance": "warn", "quote": "coderabbit being the worst while (presumeably) advertising the most", "excerpt": "coderabbit being the worst while (presumeably) advertising the most seems to be check out at least, wouldn't believe the recall % seems bogus.", "context": "", "use_case": "AI code review", "switched_from": "", "story": "We built a real-world benchmark for AI code review"}]}], "praise": [{"label": "Catches issues", "summary": "Teams using it at work say it finds a lot of useful problems.", "quotes": [{"id": 788796768, "item_id": 49299798, "url": "https://news.ycombinator.com/item?id=49299798", "by": "ryanchants", "date": "2026-08-14", "stance": "recommend", "quote": "We use CodeRabbit at work, which catches good stuff.", "excerpt": "Increasingly not. We use CodeRabbit at work, which catches good stuff. And I have my own gauntlet that I run code through. https://github.com/jacquardlabs/gauntlet", "context": "", "use_case": "automated code review", "switched_from": "", "story": "Ask HN: Does a human still review your code?"}, {"id": 774512208, "item_id": 48407013, "url": "https://news.ycombinator.com/item?id=48407013", "by": "atestu", "date": "2026-06-04", "stance": "recommend", "quote": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.", "excerpt": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot. I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed. Coderabbit just came out with their own PR review UI that's great for big PRs, it groups files together etc. https://www.coderabbit.ai/blog/introducing-atlas-the-first-ai-native", "context": "", "use_case": "AI pull request review", "switched_from": "", "story": "Alibaba/Open-Code-Review"}, {"id": 736183104, "item_id": 46011444, "url": "https://news.ycombinator.com/item?id=46011444", "by": "bebop", "date": "2025-11-21", "stance": "recommend", "quote": "We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it.", "excerpt": "We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it. Might be worth a look. Not affiliated in any way.", "context": "", "use_case": "automated code reviews", "switched_from": "", "story": "Command Lines"}]}, {"label": "PR integration", "summary": "Runs automated reviews directly on GitHub PRs and merge requests.", "quotes": [{"id": 777548032, "item_id": 48596752, "url": "https://news.ycombinator.com/item?id=48596752", "by": "jcubic", "date": "2026-06-19", "stance": "recommend", "quote": "I mostly use CodeRabbit via GitHub PR", "excerpt": "I mostly use CodeRabbit via GitHub PR https://www.coderabbit.ai/", "context": "", "use_case": "AI code review", "switched_from": "", "story": "Ask HN: What tools are you using for AI-assisted code review?"}, {"id": 799885715, "item_id": 49992857, "url": "https://news.ycombinator.com/item?id=49992857", "by": "mooseisloose", "date": "2026-10-07", "stance": "recommend", "quote": "plus automated reviews from coderabbit in the repo", "excerpt": "I'm the maintainer of Google Workspace MCP (https://github.com/taylorwilsdon/google_workspace_mcp), a project that started more as a learning exercise than anything else but has grown into one of the most popular open source MCP servers out there today. It's been time consuming and at times overwhelming, but I can honestly say that it's also been one of the most fascinating periods of my 20+ year history of writing c", "context": "open source maintainer", "use_case": "automated PR reviews", "switched_from": "", "story": "Workspace MCP v2 \u2013 Musings from the past 18 months building open source AI tools"}, {"id": 782466208, "item_id": 48904138, "url": "https://news.ycombinator.com/item?id=48904138", "by": "t-writescode", "date": "2026-07-14", "stance": "neutral", "quote": "I use AI-powered auto-complete, search and CodeRabbit for MRs.", "excerpt": "I got a high rating because I use AI-powered auto-complete, search and CodeRabbit for MRs. I'm suspicious. Perhaps the explanations provided by the hover-overs is less than clear?", "context": "", "use_case": "merge request review", "switched_from": "", "story": "Show HN: Benchmark your eng team's AI agent maturity in 5 minutes"}]}, {"label": "Pricing", "summary": "Seen as a good deal at a flat $30/month per developer, and free for open source projects.", "quotes": [{"id": 774512208, "item_id": 48407013, "url": "https://news.ycombinator.com/item?id=48407013", "by": "atestu", "date": "2026-06-04", "stance": "recommend", "quote": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.", "excerpt": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot. I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed. Coderabbit just came out with their own PR review UI that's great for big PRs, it groups files together etc. https://www.coderabbit.ai/blog/introducing-atlas-the-first-ai-native", "context": "", "use_case": "AI pull request review", "switched_from": "", "story": "Alibaba/Open-Code-Review"}, {"id": 788412304, "item_id": 49275769, "url": "https://news.ycombinator.com/item?id=49275769", "by": "smb06", "date": "2026-08-12", "stance": "recommend", "quote": "Congrats to the CodeRabbit team.", "excerpt": "Congrats to the CodeRabbit team. Key points: 1. GitHub is on pace for 14x more commits this year, and at companies in the 90th percentile of coding-agent adoption, agents now open 35% of PRs. The backlog has moved from tickets to PRs. 2. Diff-centric PR review breaks down at agent scale. Reviewing a 3,000-line agent PR line by line needs a whole new way of explainig what the agent wrote. 3. $10M committed over the ne", "context": "", "use_case": "AI code review", "switched_from": "", "story": "CodeRabbit raises a $143M Series C at a $1.5B valuation"}]}, {"label": "Wider context", "summary": "Aware of files outside the diff and the rest of the edited file.", "quotes": [{"id": 741573312, "item_id": 46348332, "url": "https://news.ycombinator.com/item?id=46348332", "by": "howToTestFE", "date": "2025-12-21", "stance": "recommend", "quote": "i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff", "excerpt": "while this approach is useful, i think the diff is too small to catch a lot of bugs. i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff, and definitely can see the rest of the file your are editing (not just the lines in the diff)", "context": "", "use_case": "AI code review", "switched_from": "", "story": "Get an AI code review in 10 seconds"}]}, {"label": "Large PR UI", "summary": "A newer review interface groups files together, which helps with big PRs.", "quotes": [{"id": 774512208, "item_id": 48407013, "url": "https://news.ycombinator.com/item?id=48407013", "by": "atestu", "date": "2026-06-04", "stance": "recommend", "quote": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.", "excerpt": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot. I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed. Coderabbit just came out with their own PR review UI that's great for big PRs, it groups files together etc. https://www.coderabbit.ai/blog/introducing-atlas-the-first-ai-native", "context": "", "use_case": "AI pull request review", "switched_from": "", "story": "Alibaba/Open-Code-Review"}]}], "caveats": [{"label": "Missed bugs", "summary": "Some found bugs and vulnerabilities that slipped past its reviews.", "quotes": [{"id": 795263489, "item_id": 49703968, "url": "https://news.ycombinator.com/item?id=49703968", "by": "dlahoda", "date": "2026-09-14", "stance": "compare", "quote": "finds bugs missed by coderabitai, devin-integration-bot, codex and copilot", "excerpt": "I would and do. works perfect https://github.com/dzmitry-lahoda/dz/tree/main/agents/skills/code-review burns half of day sub of astra for 200 USD. runs 1 hour on our repo. finds bugs missed by coderabitai, devin-integration-bot, codex and copilot (I ask them first until nothing found, yet my orchestration finds more). I do not hardcode our application in orchestration, but run subagent for applicationdomainproduct de", "context": "", "use_case": "PR code review", "switched_from": "", "story": "GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?"}, {"id": 792298946, "item_id": 49518684, "url": "https://news.ycombinator.com/item?id=49518684", "by": "eskibars", "date": "2026-09-01", "stance": "neutral", "quote": "no problem with CodeRabbit", "excerpt": "Author here. I built ZeroQuarry, and I was considering deploying an open source link shortener or using a SaaS one. I googled around and then found iShortn, so ran the iShortn scan with it. I found a bunch of vulnerabilities, which I sent to the maintainer and have now been patched, but some of the most interesting ones I found were that many of these vulnerabilities were actually crafted by (or at least reviewed by)", "context": "", "use_case": "AI code review", "switched_from": "", "story": "What AI code review misses: SSRF and more"}, {"id": 750288944, "item_id": 46893059, "url": "https://news.ycombinator.com/item?id=46893059", "by": "kachapopopow", "date": "2026-02-04", "stance": "warn", "quote": "coderabbit being the worst while (presumeably) advertising the most", "excerpt": "coderabbit being the worst while (presumeably) advertising the most seems to be check out at least, wouldn't believe the recall % seems bogus.", "context": "", "use_case": "AI code review", "switched_from": "", "story": "We built a real-world benchmark for AI code review"}]}, {"label": "Superficial reviews", "summary": "Mostly flags typos and small errors and does not address architecture or the substance of a change.", "quotes": [{"id": 789583408, "item_id": 49348963, "url": "https://news.ycombinator.com/item?id=49348963", "by": "crabbone", "date": "2026-08-18", "stance": "neutral", "quote": "I used CodeRabbit at work, and I have mixed feelings about it.", "excerpt": "1. I'm not sure what CodeRabbit has to do with the article... It's obviously an advertisement, but it's merged into the text of the article, which I find bizarre. As an aside, I used CodeRabbit at work, and I have mixed feelings about it. I'm not entirely against using it or a similar tool, but people often treat the comments from CodeRabbit as a gospel, and they can harm their code as a result. Also, I've never seen", "context": "", "use_case": "code review", "switched_from": "", "story": "Kent Beck: Composable Tests"}, {"id": 797998416, "item_id": 49874901, "url": "https://news.ycombinator.com/item?id=49874901", "by": "quatotor", "date": "2026-09-28", "stance": "warn", "quote": "I have similar experience with coderabbit we use at work.", "excerpt": "I have similar experience with coderabbit we use at work. On the other hand codex with astra I use locally is way better. Still AI review is very different from human review. AI is better in paying attention and in finding bugs but it is incapable to detect code smells, wrong architectural decisions or domain errors. Although AI is still way better in code reviews than in writing code. It make sense to use it as anot", "context": "", "use_case": "AI code review", "switched_from": "", "story": "There is more to code review than (automatable) detection"}]}, {"label": "False positives", "summary": "One team stopped relying on it after it flagged mostly false positives.", "quotes": [{"id": 779973616, "item_id": 48748351, "url": "https://news.ycombinator.com/item?id=48748351", "by": "anee769", "date": "2026-07-01", "stance": "warn", "quote": "we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so eventually we stopped relying on it.", "excerpt": "The hardest part of review tools like this is signal-to-noise \u2014 one round of false positives and people start reflex-accepting or muting it. How does Ox decide what's worth flagging on a given PR, and does it dedupe against pre-existing debt so it only surfaces what the change actually introduced? In my company, we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so e", "context": "uses it at their company", "use_case": "AI code review", "switched_from": "", "story": "Show HN: Ox \u2013 an AI agent that catches tech debt before it's committed"}]}, {"label": "Over-trust", "summary": "Developers may treat its comments as gospel and harm their code.", "quotes": [{"id": 789583408, "item_id": 49348963, "url": "https://news.ycombinator.com/item?id=49348963", "by": "crabbone", "date": "2026-08-18", "stance": "neutral", "quote": "I used CodeRabbit at work, and I have mixed feelings about it.", "excerpt": "1. I'm not sure what CodeRabbit has to do with the article... It's obviously an advertisement, but it's merged into the text of the article, which I find bizarre. As an aside, I used CodeRabbit at work, and I have mixed feelings about it. I'm not entirely against using it or a similar tool, but people often treat the comments from CodeRabbit as a gospel, and they can harm their code as a result. Also, I've never seen", "context": "", "use_case": "code review", "switched_from": "", "story": "Kent Beck: Composable Tests"}]}, {"label": "Marketing skepticism", "summary": "Some doubt its advertised claims and dislike its advertising.", "quotes": [{"id": 750288944, "item_id": 46893059, "url": "https://news.ycombinator.com/item?id=46893059", "by": "kachapopopow", "date": "2026-02-04", "stance": "warn", "quote": "coderabbit being the worst while (presumeably) advertising the most", "excerpt": "coderabbit being the worst while (presumeably) advertising the most seems to be check out at least, wouldn't believe the recall % seems bogus.", "context": "", "use_case": "AI code review", "switched_from": "", "story": "We built a real-world benchmark for AI code review"}, {"id": 789583408, "item_id": 49348963, "url": "https://news.ycombinator.com/item?id=49348963", "by": "crabbone", "date": "2026-08-18", "stance": "neutral", "quote": "I used CodeRabbit at work, and I have mixed feelings about it.", "excerpt": "1. I'm not sure what CodeRabbit has to do with the article... It's obviously an advertisement, but it's merged into the text of the article, which I find bizarre. As an aside, I used CodeRabbit at work, and I have mixed feelings about it. I'm not entirely against using it or a similar tool, but people often treat the comments from CodeRabbit as a gospel, and they can harm their code as a result. Also, I've never seen", "context": "", "use_case": "code review", "switched_from": "", "story": "Kent Beck: Composable Tests"}]}], "who": [{"by": "bemeeker", "context": "solo maintainer", "url": "https://news.ycombinator.com/item?id=50131519", "date": "2026-10-17"}, {"by": "mooseisloose", "context": "open source maintainer", "url": "https://news.ycombinator.com/item?id=49992857", "date": "2026-10-07"}], "tags": ["for PR review", "for teams", "for open source maintainers", "for GitHub users"], "use_cases": ["ai code review", "code review", "understanding merge requests", "ast-grep rule ideas", "automated pr reviews", "pr code review"], "compared": [{"slug": "codex", "name": "Codex", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "copilot", "name": "Copilot", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gpt-astra", "name": "GPT Astra", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 789374512, "item_id": 49335907, "url": "https://news.ycombinator.com/item?id=49335907", "by": "juanpflores", "date": "2026-08-17", "stance": "recommend", "quote": "Coderabbit DX staff here. We have a new interface we are exploring for code review called change stack.", "excerpt": "Hey there! Coderabbit DX staff here. We have a new interface we are exploring for code review called change stack. Would love to hear your feedback on it and learn of the issues you mentioned above. If you have a PR we could take a look at I can bring this to the tea,", "context": "CodeRabbit DX staff", "use_case": "code review", "switched_from": "", "story": "Ask HN: What tools are you using for human code review of AI-assisted code?"}], "threads": [{"url": "https://news.ycombinator.com/item?id=50186182", "title": "Ask HN: What AI tools help me understand a MR?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50131518", "title": "Ask HN: How are you all ensuring your AI code isn't slop?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50075809", "title": "Show HN: Deslop \u2013 Oxlint rules for AI-generated TypeScript", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49992856", "title": "Workspace MCP v2 \u2013 Musings from the past 18 months building open source AI tools", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49857281", "title": "There is more to code review than (automatable) detection", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49703003", "title": "GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {"neutral": 1, "recommend": 1}, "2026-01": {}, "2026-02": {"warn": 1, "neutral": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 3}, "2026-07": {"warn": 1, "neutral": 2}, "2026-08": {"recommend": 2, "neutral": 1}, "2026-09": {"neutral": 1, "compare": 1, "warn": 1}, "2026-10": {"recommend": 1, "neutral": 2}}, "quotes": [{"id": 803039776, "item_id": 50189986, "url": "https://news.ycombinator.com/item?id=50189986", "by": "juanpflores", "date": "2026-10-22", "stance": "recommend", "quote": "Would recommend checking out coderabbit change stack. it essentially does exactly what you're looking for", "excerpt": "Would recommend checking out coderabbit change stack. it essentially does exactly what you're looking for", "context": "", "use_case": "understanding merge requests", "switched_from": "", "story": "Ask HN: What AI tools help me understand a MR?"}, {"id": 802104307, "item_id": 50131519, "url": "https://news.ycombinator.com/item?id=50131519", "by": "bemeeker", "date": "2026-10-17", "stance": "neutral", "quote": "I\u2019m also using SonarQube and CodeRabbit", "excerpt": "I\u2019ve been working on an open source project called Pando (https://github.com/trypando/pando), which is meant to help alleviate \u201cShadow AI\u201d vibecoded apps in workplaces, and give employees an outlet for what they build. With that said, it\u2019s a big project and I\u2019m a solo maintainer right now, and as a result I\u2019m using AI for much of the development process. Obviously this isn\u2019t new. AWS, Google, Meta, and pretty much ev", "context": "solo maintainer", "use_case": "AI code review", "switched_from": "", "story": "Ask HN: How are you all ensuring your AI code isn't slop?"}, {"id": 801268130, "item_id": 50079258, "url": "https://news.ycombinator.com/item?id=50079258", "by": "navs", "date": "2026-10-13", "stance": "neutral", "quote": "I started down this path after looking at what coderabbit suggested", "excerpt": "oxlint and some general ast-grep rules have pretty much been an absolute necessity for any of my LLM based code generation. I started down this path after looking at what coderabbit suggested in https://github.com/coderabbitai/ast-grep-essentials", "context": "", "use_case": "ast-grep rule ideas", "switched_from": "", "story": "Show HN: Deslop \u2013 Oxlint rules for AI-generated TypeScript"}, {"id": 799885715, "item_id": 49992857, "url": "https://news.ycombinator.com/item?id=49992857", "by": "mooseisloose", "date": "2026-10-07", "stance": "recommend", "quote": "plus automated reviews from coderabbit in the repo", "excerpt": "I'm the maintainer of Google Workspace MCP (https://github.com/taylorwilsdon/google_workspace_mcp), a project that started more as a learning exercise than anything else but has grown into one of the most popular open source MCP servers out there today. It's been time consuming and at times overwhelming, but I can honestly say that it's also been one of the most fascinating periods of my 20+ year history of writing c", "context": "open source maintainer", "use_case": "automated PR reviews", "switched_from": "", "story": "Workspace MCP v2 \u2013 Musings from the past 18 months building open source AI tools"}, {"id": 797998416, "item_id": 49874901, "url": "https://news.ycombinator.com/item?id=49874901", "by": "quatotor", "date": "2026-09-28", "stance": "warn", "quote": "I have similar experience with coderabbit we use at work.", "excerpt": "I have similar experience with coderabbit we use at work. On the other hand codex with astra I use locally is way better. Still AI review is very different from human review. AI is better in paying attention and in finding bugs but it is incapable to detect code smells, wrong architectural decisions or domain errors. Although AI is still way better in code reviews than in writing code. It make sense to use it as anot", "context": "", "use_case": "AI code review", "switched_from": "", "story": "There is more to code review than (automatable) detection"}, {"id": 795263489, "item_id": 49703968, "url": "https://news.ycombinator.com/item?id=49703968", "by": "dlahoda", "date": "2026-09-14", "stance": "compare", "quote": "finds bugs missed by coderabitai, devin-integration-bot, codex and copilot", "excerpt": "I would and do. works perfect https://github.com/dzmitry-lahoda/dz/tree/main/agents/skills/code-review burns half of day sub of astra for 200 USD. runs 1 hour on our repo. finds bugs missed by coderabitai, devin-integration-bot, codex and copilot (I ask them first until nothing found, yet my orchestration finds more). I do not hardcode our application in orchestration, but run subagent for applicationdomainproduct de", "context": "", "use_case": "PR code review", "switched_from": "", "story": "GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?"}, {"id": 792298946, "item_id": 49518684, "url": "https://news.ycombinator.com/item?id=49518684", "by": "eskibars", "date": "2026-09-01", "stance": "neutral", "quote": "no problem with CodeRabbit", "excerpt": "Author here. I built ZeroQuarry, and I was considering deploying an open source link shortener or using a SaaS one. I googled around and then found iShortn, so ran the iShortn scan with it. I found a bunch of vulnerabilities, which I sent to the maintainer and have now been patched, but some of the most interesting ones I found were that many of these vulnerabilities were actually crafted by (or at least reviewed by)", "context": "", "use_case": "AI code review", "switched_from": "", "story": "What AI code review misses: SSRF and more"}, {"id": 789583408, "item_id": 49348963, "url": "https://news.ycombinator.com/item?id=49348963", "by": "crabbone", "date": "2026-08-18", "stance": "neutral", "quote": "I used CodeRabbit at work, and I have mixed feelings about it.", "excerpt": "1. I'm not sure what CodeRabbit has to do with the article... It's obviously an advertisement, but it's merged into the text of the article, which I find bizarre. As an aside, I used CodeRabbit at work, and I have mixed feelings about it. I'm not entirely against using it or a similar tool, but people often treat the comments from CodeRabbit as a gospel, and they can harm their code as a result. Also, I've never seen", "context": "", "use_case": "code review", "switched_from": "", "story": "Kent Beck: Composable Tests"}, {"id": 788796768, "item_id": 49299798, "url": "https://news.ycombinator.com/item?id=49299798", "by": "ryanchants", "date": "2026-08-14", "stance": "recommend", "quote": "We use CodeRabbit at work, which catches good stuff.", "excerpt": "Increasingly not. We use CodeRabbit at work, which catches good stuff. And I have my own gauntlet that I run code through. https://github.com/jacquardlabs/gauntlet", "context": "", "use_case": "automated code review", "switched_from": "", "story": "Ask HN: Does a human still review your code?"}, {"id": 788412304, "item_id": 49275769, "url": "https://news.ycombinator.com/item?id=49275769", "by": "smb06", "date": "2026-08-12", "stance": "recommend", "quote": "Congrats to the CodeRabbit team.", "excerpt": "Congrats to the CodeRabbit team. Key points: 1. GitHub is on pace for 14x more commits this year, and at companies in the 90th percentile of coding-agent adoption, agents now open 35% of PRs. The backlog has moved from tickets to PRs. 2. Diff-centric PR review breaks down at agent scale. Reviewing a 3,000-line agent PR line by line needs a whole new way of explainig what the agent wrote. 3. $10M committed over the ne", "context": "", "use_case": "AI code review", "switched_from": "", "story": "CodeRabbit raises a $143M Series C at a $1.5B valuation"}, {"id": 785483600, "item_id": 49092725, "url": "https://news.ycombinator.com/item?id=49092725", "by": "smb06", "date": "2026-07-28", "stance": "neutral", "quote": "I use CodeRabbit all the time but it has a swarm of dozens of sub-agents.", "excerpt": "Depends on how you define agents. I use CodeRabbit all the time but it has a swarm of dozens of sub-agents. So am i using 1 agent or 10+?", "context": "", "use_case": "AI code review", "switched_from": "", "story": "Ask HN: How many AI agents do you actively use?"}, {"id": 782466208, "item_id": 48904138, "url": "https://news.ycombinator.com/item?id=48904138", "by": "t-writescode", "date": "2026-07-14", "stance": "neutral", "quote": "I use AI-powered auto-complete, search and CodeRabbit for MRs.", "excerpt": "I got a high rating because I use AI-powered auto-complete, search and CodeRabbit for MRs. I'm suspicious. Perhaps the explanations provided by the hover-overs is less than clear?", "context": "", "use_case": "merge request review", "switched_from": "", "story": "Show HN: Benchmark your eng team's AI agent maturity in 5 minutes"}, {"id": 779973616, "item_id": 48748351, "url": "https://news.ycombinator.com/item?id=48748351", "by": "anee769", "date": "2026-07-01", "stance": "warn", "quote": "we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so eventually we stopped relying on it.", "excerpt": "The hardest part of review tools like this is signal-to-noise \u2014 one round of false positives and people start reflex-accepting or muting it. How does Ox decide what's worth flagging on a given PR, and does it dedupe against pre-existing debt so it only surfaces what the change actually introduced? In my company, we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so e", "context": "uses it at their company", "use_case": "AI code review", "switched_from": "", "story": "Show HN: Ox \u2013 an AI agent that catches tech debt before it's committed"}, {"id": 777548032, "item_id": 48596752, "url": "https://news.ycombinator.com/item?id=48596752", "by": "jcubic", "date": "2026-06-19", "stance": "recommend", "quote": "I mostly use CodeRabbit via GitHub PR", "excerpt": "I mostly use CodeRabbit via GitHub PR https://www.coderabbit.ai/", "context": "", "use_case": "AI code review", "switched_from": "", "story": "Ask HN: What tools are you using for AI-assisted code review?"}, {"id": 775337650, "item_id": 48458603, "url": "https://news.ycombinator.com/item?id=48458603", "by": "mattsadowsky", "date": "2026-06-09", "stance": "recommend", "quote": "code rabit or any other code review tool", "excerpt": "CLAUDE.md Plan mode code rabit or any other code review tool Claude PRO MAX subscription or Codex", "context": "", "use_case": "code review", "switched_from": "", "story": "Ask HN: What is the AI setup for an experienced dev starting on a new project?"}, {"id": 774512208, "item_id": 48407013, "url": "https://news.ycombinator.com/item?id=48407013", "by": "atestu", "date": "2026-06-04", "stance": "recommend", "quote": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.", "excerpt": "We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot. I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed. Coderabbit just came out with their own PR review UI that's great for big PRs, it groups files together etc. https://www.coderabbit.ai/blog/introducing-atlas-the-first-ai-native", "context": "", "use_case": "AI pull request review", "switched_from": "", "story": "Alibaba/Open-Code-Review"}, {"id": 753738897, "item_id": 47108681, "url": "https://news.ycombinator.com/item?id=47108681", "by": "Merad", "date": "2026-02-21", "stance": "neutral", "quote": "Then I have both Claude and CodeRabbit do code review passes", "excerpt": "I've been working off and on on a vibe coded FP language and transpiler - mostly just to get more experience with Claude Code and see how it handles complex real world projects. I've settled on a very similar flow, though I use three documents: plan, context, task list. Multiple rounds of iteration when planning a feature. After completion, have a clean session do an audit to confirm that everything was implemented p", "context": "", "use_case": "code review", "switched_from": "", "story": "How I use Claude Code: Separation of planning and execution"}, {"id": 750288944, "item_id": 46893059, "url": "https://news.ycombinator.com/item?id=46893059", "by": "kachapopopow", "date": "2026-02-04", "stance": "warn", "quote": "coderabbit being the worst while (presumeably) advertising the most", "excerpt": "coderabbit being the worst while (presumeably) advertising the most seems to be check out at least, wouldn't believe the recall % seems bogus.", "context": "", "use_case": "AI code review", "switched_from": "", "story": "We built a real-world benchmark for AI code review"}, {"id": 741573312, "item_id": 46348332, "url": "https://news.ycombinator.com/item?id=46348332", "by": "howToTestFE", "date": "2025-12-21", "stance": "recommend", "quote": "i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff", "excerpt": "while this approach is useful, i think the diff is too small to catch a lot of bugs. i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff, and definitely can see the rest of the file your are editing (not just the lines in the diff)", "context": "", "use_case": "AI code review", "switched_from": "", "story": "Get an AI code review in 10 seconds"}, {"id": 741022512, "item_id": 46313907, "url": "https://news.ycombinator.com/item?id=46313907", "by": "sailfast", "date": "2025-12-18", "stance": "neutral", "quote": "How many more bugs does it produce if we use CodeRabbit to review PRs?", "excerpt": "How many more bugs does it produce if we use CodeRabbit to review PRs? I assume the number will be less? (Asking seriously and hopefully if the product will help or would\u2019ve caught the bugs, while also pointing out the natural conclusion of the article is to purchase your service :) )", "context": "", "use_case": "PR review", "switched_from": "", "story": "AI helps ship faster but it produces 1.7\u00d7 more bugs"}, {"id": 736183104, "item_id": 46011444, "url": "https://news.ycombinator.com/item?id=46011444", "by": "bebop", "date": "2025-11-21", "stance": "recommend", "quote": "We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it.", "excerpt": "We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it. Might be worth a look. Not affiliated in any way.", "context": "", "use_case": "automated code reviews", "switched_from": "", "story": "Command Lines"}]}