{"slug": "jules", "name": "Jules", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 6, "commenters": 16, "warners": 2, "score": 5.33, "rising": -1.96, "first": "2025-11-18", "latest": "2026-10-26", "why": "I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 7, "neutral": 9, "compare": 0, "warn": 2}, "spark": [1, 0, 2, 1, 2, 1, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful.", "kind": "", "icon": false, "domain": "jules.google", "github_repo": null, "official_url": "https://jules.google", "pricing": "", "aliases": ["Jules", "Google Jules"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 769435264, "item_id": 48089704, "url": "https://news.ycombinator.com/item?id=48089704", "by": "simonpure", "date": "2026-05-10", "version": null, "stance": "recommend", "quote": "I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful.", "excerpt": "Thanks! I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful. I like that I can use it from my phone too. It took a bit of trial and error but I came up with a good ralph loop between GitHub Actions and Google Jules using the Jules API. So basically I have Jules extend its TODO.md with the next set of tasks and open a PR then run a GitHub Action with a few checks, auto-merge, and t", "context": "", "use_case": "autonomous coding loop", "switched_from": "", "story": "Ask HN: What Are You Working On? (May 2026)"}, {"id": 763130624, "item_id": 47695664, "url": "https://news.ycombinator.com/item?id=47695664", "by": "tasuki", "date": "2026-04-08", "version": null, "stance": "recommend", "quote": "I use Google Jules and also appreciate being able to nudge it forward", "excerpt": "> One of the ideas I like about opencode is the ability to prompt and such from a web browser. So I'm curious if that is the client-server architecture you are talking about, or if it's something else. Yes, this is what I meant. And yes it's ok that you like this about opencode :) > For reference, I used replit for some vibe-ish coding for a little bit and really liked that I could easily prompt and view output on my", "context": "", "use_case": "Async coding agent tasks", "switched_from": "", "story": "I've Sold Out"}, {"id": 761423585, "item_id": 47588974, "url": "https://news.ycombinator.com/item?id=47588974", "by": "tasuki", "date": "2026-03-31", "version": null, "stance": "recommend", "quote": "I use Google Jules (free tier) on a toy project much more heavily and can't complain.", "excerpt": "I use Gemini-CLI at work, and haven't noticed anything. I use Google Jules (free tier) on a toy project much more heavily and can't complain. I think sometimes the prompts take longer than they used to, but I couldn't care less. I'm not in a hurry.", "context": "", "use_case": "Coding agent on a toy project", "switched_from": "", "story": "Anthropic: Claude Code users hitting usage limits 'way faster than expected'"}, {"id": 757296432, "item_id": 47331027, "url": "https://news.ycombinator.com/item?id=47331027", "by": "simonpure", "date": "2026-03-10", "version": null, "stance": "recommend", "quote": "I've been impressed by Google Jules", "excerpt": "I've been impressed by Google Jules since the Gemini 3.1 Pro update. Sometimes it's been working on a task for 4h. I've now put it in a ralph loop using a Github Action to call itself and auto merge PRs after the linter, formatter and tests pass. It does still occasionally want my approval, but most of the time I just say Sounds great! It's currently burning through the TESTING.md backlog: https://github.com/alpeware", "context": "", "use_case": "", "switched_from": "", "story": "You hired the AI to write the tests. Of course they pass"}, {"id": 750530032, "item_id": 46908127, "url": "https://news.ycombinator.com/item?id=46908127", "by": "degurechaff", "date": "2026-02-05", "version": null, "stance": "recommend", "quote": "you can use jules and spend zero dollar on it", "excerpt": "well, you can use jules and spend zero dollar on it. I also create similiar project like this, c11 compiler in rust using AI agent + 1 developer(https://github.com/bungcip/cendol). not fully automated like anthophic did, but at least i can understand what it did.", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 792589232, "item_id": 49536827, "url": "https://news.ycombinator.com/item?id=49536827", "by": "Osteen14", "date": "2026-09-02", "version": null, "stance": "warn", "quote": "I use Jules myself, and it hallucinates like hell", "excerpt": "I use Jules myself, and it hallucinates like hell, but I can't afford Claude code. Honestly, I feel it struggles to understand my prompts. No wonder how good they are. Yeah, that's basically it. But why are you doing your analytics on agent coding experiences?", "context": "can't afford Claude Code", "use_case": "coding agent", "switched_from": "", "story": "Ask HN: Anyone struggling to do data work with Claude Code or codex?"}, {"id": 767283173, "item_id": 47955198, "url": "https://news.ycombinator.com/item?id=47955198", "by": "martinald", "date": "2026-04-29", "version": null, "stance": "warn", "quote": "are miles ahead of Gemini CLI/Jules/Antigravity", "excerpt": "Gemini is not reliable whatsoever: https://openrouter.ai/google/gemini-3.1-pro-preview/uptime (the orange chart is either AI studio or Vertex, I suspect AI studio, but it's not good either way). The reason you don't hear people complaining (esp on HN) is because noone is using Gemini with coding agents. Claude Code, Codex (and IMO OpenCode et al with open weights models) are miles ahead of Gemini CLI/Jules/Antigravit", "context": "", "use_case": "", "switched_from": "", "story": "Alphabet Announces First Quarter 2026 Results"}]}], "who": [{"by": "vardhan1237", "context": "PaperPilot developer", "url": "https://news.ycombinator.com/item?id=50242458", "date": "2026-10-26"}, {"by": "Zaki101Aslam", "context": "Transitioning from Windows to Linux", "url": "https://news.ycombinator.com/item?id=47021526", "date": "2026-02-14"}], "tags": [], "use_cases": ["coding agent", "async unit tests and docs", "autonomous coding loop", "sandboxed coding sessions", "async coding agent tasks", "coding agent on a toy project"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "google-antigravity", "name": "Google Antigravity", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "github-copilot", "name": "GitHub Copilot", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "gemini-pro", "name": "Gemini Pro", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gemini-cli", "name": "Gemini CLI", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48085993", "title": "Ask HN: What Are You Working On? (May 2026)", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=46491486", "title": "Claude Code On-the-Go", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50238739", "title": "PaperPilot \u2013 Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50000312", "title": "item 50000312", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49526186", "title": "Ask HN: Anyone struggling to do data work with Claude Code or codex?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47954024", "title": "Alphabet Announces First Quarter 2026 Results", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 1, "recommend": 1}, "2025-12": {"neutral": 1}, "2026-01": {"neutral": 2, "recommend": 2}, "2026-02": {"recommend": 1, "neutral": 1}, "2026-03": {"recommend": 2}, "2026-04": {"recommend": 1, "neutral": 1, "warn": 1}, "2026-05": {"neutral": 1}, "2026-06": {}, "2026-07": {}, "2026-08": {}, "2026-09": {"warn": 1}, "2026-10": {"neutral": 2}}, "versions": [], "version_unnamed": 0, "quotes": [{"id": 803879329, "item_id": 50242458, "url": "https://news.ycombinator.com/item?id=50242458", "by": "vardhan1237", "date": "2026-10-26", "version": null, "stance": "neutral", "quote": "Jules for asynchronous sub-tasks (like spinning up isolated unit tests and docs in parallel containers)", "excerpt": "Thanks for checking out the docs! We used a hybrid workflow: Antigravity IDE paired with Jules for asynchronous sub-tasks (like spinning up isolated unit tests and docs in parallel containers). Having a strict test-first harness where every PR has to run against real PDF byte fixtures (zero mocks) and compile across CLI, WASM, and MCP kept the codebase consistent even when moving fast.", "context": "PaperPilot developer", "use_case": "async unit tests and docs", "switched_from": "", "story": "PaperPilot \u2013 Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP"}, {"id": 800005008, "item_id": 50000313, "url": "https://news.ycombinator.com/item?id=50000313", "by": "Zeruxe", "date": "2026-10-07", "version": null, "stance": "neutral", "quote": "Jules is a google model that works off my requests rather than tokens", "excerpt": "I wanted a way to perform market analysis easier, I just didn't have a way to do so fast, well I tried using the Gpt and Claude chat interface, but then I have to keep track of everything it spits out, and I have to genuinely prompt in such a detailed manner everytime for it to yield good results, because prompting is a skill whether we like it or not, the LLM's can't just assume what we want or need and get it corre", "context": "", "use_case": "Coding agent", "switched_from": "", "story": null}, {"id": 792589232, "item_id": 49536827, "url": "https://news.ycombinator.com/item?id=49536827", "by": "Osteen14", "date": "2026-09-02", "version": null, "stance": "warn", "quote": "I use Jules myself, and it hallucinates like hell", "excerpt": "I use Jules myself, and it hallucinates like hell, but I can't afford Claude code. Honestly, I feel it struggles to understand my prompts. No wonder how good they are. Yeah, that's basically it. But why are you doing your analytics on agent coding experiences?", "context": "can't afford Claude Code", "use_case": "coding agent", "switched_from": "", "story": "Ask HN: Anyone struggling to do data work with Claude Code or codex?"}, {"id": 769435264, "item_id": 48089704, "url": "https://news.ycombinator.com/item?id=48089704", "by": "simonpure", "date": "2026-05-10", "version": null, "stance": "recommend", "quote": "I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful.", "excerpt": "Thanks! I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful. I like that I can use it from my phone too. It took a bit of trial and error but I came up with a good ralph loop between GitHub Actions and Google Jules using the Jules API. So basically I have Jules extend its TODO.md with the next set of tasks and open a PR then run a GitHub Action with a few checks, auto-merge, and t", "context": "", "use_case": "autonomous coding loop", "switched_from": "", "story": "Ask HN: What Are You Working On? (May 2026)"}, {"id": 769424481, "item_id": 48089030, "url": "https://news.ycombinator.com/item?id=48089030", "by": "simonpure", "date": "2026-05-10", "version": null, "stance": "neutral", "quote": "have used it to experiment with Gemini's cloud agent Google Jules", "excerpt": "I've been working on a pure Clojure implementation of WebRTC Data Channels (SCTP over DTLS over UDP). The library provides a minimal, dependency-free (except for Clojure itself) way to establish peer-to-peer data channels on the JVM. I've always wanted this and have used it to experiment with Gemini's cloud agent Google Jules. https://github.com/alpeware/datachannel-clj", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: What Are You Working On? (May 2026)"}, {"id": 767283173, "item_id": 47955198, "url": "https://news.ycombinator.com/item?id=47955198", "by": "martinald", "date": "2026-04-29", "version": null, "stance": "warn", "quote": "are miles ahead of Gemini CLI/Jules/Antigravity", "excerpt": "Gemini is not reliable whatsoever: https://openrouter.ai/google/gemini-3.1-pro-preview/uptime (the orange chart is either AI studio or Vertex, I suspect AI studio, but it's not good either way). The reason you don't hear people complaining (esp on HN) is because noone is using Gemini with coding agents. Claude Code, Codex (and IMO OpenCode et al with open weights models) are miles ahead of Gemini CLI/Jules/Antigravit", "context": "", "use_case": "", "switched_from": "", "story": "Alphabet Announces First Quarter 2026 Results"}, {"id": 766322545, "item_id": 47895159, "url": "https://news.ycombinator.com/item?id=47895159", "by": "8ytecoder", "date": "2026-04-24", "version": null, "stance": "neutral", "quote": "Essentially everything happens in a sandbox", "excerpt": "I use Claude \u201con the web\u201d or Google Jules. Essentially everything happens in a sandbox - so yolo isn\u2019t a huge risk. You can even box its network access. You review the PR at the end or steer it if it\u2019s veering off course.", "context": "", "use_case": "sandboxed coding sessions", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}, {"id": 763130624, "item_id": 47695664, "url": "https://news.ycombinator.com/item?id=47695664", "by": "tasuki", "date": "2026-04-08", "version": null, "stance": "recommend", "quote": "I use Google Jules and also appreciate being able to nudge it forward", "excerpt": "> One of the ideas I like about opencode is the ability to prompt and such from a web browser. So I'm curious if that is the client-server architecture you are talking about, or if it's something else. Yes, this is what I meant. And yes it's ok that you like this about opencode :) > For reference, I used replit for some vibe-ish coding for a little bit and really liked that I could easily prompt and view output on my", "context": "", "use_case": "Async coding agent tasks", "switched_from": "", "story": "I've Sold Out"}, {"id": 761423585, "item_id": 47588974, "url": "https://news.ycombinator.com/item?id=47588974", "by": "tasuki", "date": "2026-03-31", "version": null, "stance": "recommend", "quote": "I use Google Jules (free tier) on a toy project much more heavily and can't complain.", "excerpt": "I use Gemini-CLI at work, and haven't noticed anything. I use Google Jules (free tier) on a toy project much more heavily and can't complain. I think sometimes the prompts take longer than they used to, but I couldn't care less. I'm not in a hurry.", "context": "", "use_case": "Coding agent on a toy project", "switched_from": "", "story": "Anthropic: Claude Code users hitting usage limits 'way faster than expected'"}, {"id": 757296432, "item_id": 47331027, "url": "https://news.ycombinator.com/item?id=47331027", "by": "simonpure", "date": "2026-03-10", "version": null, "stance": "recommend", "quote": "I've been impressed by Google Jules", "excerpt": "I've been impressed by Google Jules since the Gemini 3.1 Pro update. Sometimes it's been working on a task for 4h. I've now put it in a ralph loop using a Github Action to call itself and auto merge PRs after the linter, formatter and tests pass. It does still occasionally want my approval, but most of the time I just say Sounds great! It's currently burning through the TESTING.md backlog: https://github.com/alpeware", "context": "", "use_case": "", "switched_from": "", "story": "You hired the AI to write the tests. Of course they pass"}, {"id": 752344417, "item_id": 47021526, "url": "https://news.ycombinator.com/item?id=47021526", "by": "Zaki101Aslam", "date": "2026-02-14", "version": null, "stance": "neutral", "quote": "I used Jules agent to help build and refine the repository.", "excerpt": "I'm currently transitioning from Windows to Linux and getting familiar with LibreOffice. To make the switch smoother, I created a tool that maps (almost) all MS Office shortcuts to LibreOffice equivalents. I used Jules agent to help build and refine the repository. I figured others making the same transition might find it useful. Would love feedback from the community about improvements to the mapping!", "context": "Transitioning from Windows to Linux", "use_case": "building a shortcut-mapping repo", "switched_from": "", "story": "Use Microsoft Office Shortcuts in Libre Office"}, {"id": 750530032, "item_id": 46908127, "url": "https://news.ycombinator.com/item?id=46908127", "by": "degurechaff", "date": "2026-02-05", "version": null, "stance": "recommend", "quote": "you can use jules and spend zero dollar on it", "excerpt": "well, you can use jules and spend zero dollar on it. I also create similiar project like this, c11 compiler in rust using AI agent + 1 developer(https://github.com/bungcip/cendol). not fully automated like anthophic did, but at least i can understand what it did.", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}, {"id": 746441616, "item_id": 46652601, "url": "https://news.ycombinator.com/item?id=46652601", "by": "embedding-shape", "date": "2026-01-16", "version": null, "stance": "neutral", "quote": "Google's Jules made one commit", "excerpt": "Looks like a bunch of different users (including Google's Jules made one commit) been contributing to the codebase, and the recent \"fixes\" includes switching between various git users. https://gist.github.com/embedding-shapes/d09225180ea3236f18039ca7a24b7ecb This to me seems to raise more questions than it answers.", "context": "", "use_case": "", "switched_from": "", "story": "Scaling long-running autonomous coding"}, {"id": 746130720, "item_id": 46633170, "url": "https://news.ycombinator.com/item?id=46633170", "by": "bjackman", "date": "2026-01-15", "version": null, "stance": "recommend", "quote": "to me the underlying product model is obviously the right one.", "excerpt": "I use https://jules.google. The UI is obviously vibe-coded garbage but the underlying system works. And most of the time you don't have to open the UI after you've set it running you just comment on the Github PR. This is clearly an unloved \"lab\" project that Google will most likely kill but to me the underlying product model is obviously the right one. I assume Microsoft got this model right first with the \"assign i", "context": "", "use_case": "async coding agent via GitHub PRs", "switched_from": "", "story": "Bubblewrap: A nimble way to prevent agents from accessing your .env files"}, {"id": 743912480, "item_id": 46494530, "url": "https://news.ycombinator.com/item?id=46494530", "by": "zeckalpha", "date": "2026-01-04", "version": null, "stance": "recommend", "quote": "Jules and GitHub Copilot Agent suffice for similar workflows with less setup.", "excerpt": "Jules and GitHub Copilot Agent suffice for similar workflows with less setup. I've not tried Claude Code for Web but assume it would be similar. https://code.claude.com/docs/en/claude-code-on-the-web", "context": "", "use_case": "Async coding agent", "switched_from": "", "story": "Claude Code On-the-Go"}, {"id": 743886064, "item_id": 46492879, "url": "https://news.ycombinator.com/item?id=46492879", "by": "smarx007", "date": "2026-01-04", "version": null, "stance": "neutral", "quote": "The output from Jules is a PR.", "excerpt": "The output from Jules is a PR. And then it's a toss-up between \"spot on, let's merge\" and \"nah, needs more work, I will check out the branch and fix it properly when I am the keyboard\". And you see the current diff on the webpage while the agent is working.", "context": "", "use_case": "", "switched_from": "", "story": "Claude Code On-the-Go"}, {"id": 739960163, "item_id": 46247510, "url": "https://news.ycombinator.com/item?id=46247510", "by": "narayanahari", "date": "2025-12-12", "version": null, "stance": "neutral", "quote": "Some tools already hint at this. GitHub Copilot Agents, Jules, Codex and Claude Code for Web.", "excerpt": "We keep celebrating how fast we can code with vibe coding tools like Cursor and Copilot. What we rarely talk about is the cost. Constant context switching cost. The autocomplete feels fast but the tool keeps pulling me back for micro checks. Most of the time I feel like I am just staring at the screen waiting for it to finish a thought, then correcting it, then nudging it again. I am unable to queue new tasks up. It ", "context": "", "use_case": "asynchronous coding agents", "switched_from": "", "story": "The Vibe Coding Landscape: The Orchestrator Fix"}, {"id": 736819362, "item_id": 46051210, "url": "https://news.ycombinator.com/item?id=46051210", "by": "simonw", "date": "2025-11-25", "version": null, "stance": "recommend", "quote": "The easiest way to do that today is to use one of the cloud-based asynchronous coding agent tools", "excerpt": "The easiest way to do that today is to use one of the cloud-based asynchronous coding agent tools - like https://claude.ai/code or https://chatgpt.com/codex or https://jules.google/ They run the agent in a VM somewhere on their own infrastructure. Any leaks are limited to the code and credentials that you deliberately make available to those tools.", "context": "", "use_case": "", "switched_from": "", "story": "Google Antigravity exfiltrates data via indirect prompt injection attack"}, {"id": 735521009, "item_id": 45970063, "url": "https://news.ycombinator.com/item?id=45970063", "by": "dygd", "date": "2025-11-18", "version": null, "stance": "neutral", "quote": "The also launched a coding agent Jules: https://jules.google/", "excerpt": "The also launched a coding agent Jules: https://jules.google/", "context": "", "use_case": "", "switched_from": "", "story": "Google Antigravity"}]}