Rill browser takes a radically different approach to AI workflows by running Claude Code and Codex natively alongside your tabs. What worked: managing multi-source research across windows and letting background agents run tasks while browsing feels smooth. What didn't: desktop-only limitation on Apple Silicon currently breaks mobile workflows. One thing to improve: adding mobile support or a companion app so workflows can sync across devices would make it a complete daily driver. 🔗 rill.love
View on XRill Browser
- $100
- Reward pool
- Oct 15, 2026 – Oct 18, 2026
- Window
- Top 10,000
- Open to
- 17
- Reviews so far
Reach across all posts
17 posts · public numbers from X
- 4.9K
- views
- 194
- likes
- 33
- reposts
- 54
- replies
- 38
- bookmarks
- 7
- quotes
Test Drive brief
Download Rill free for Apple silicon Macs (https://rill.love/). It runs on your existing Claude Code or Codex plan. Use it your way: browse, research, debug or build, and hand any page to your agent whenever it helps. Share how it fit your workflow, what worked, what didn't, and one thing you'd improve.
Your post must include
- Fits in 740 characters
- Oct 15, 2026, 12:00 AM
- Starts
- Oct 18, 2026, 11:59 PM
- Ends
- rill.love ↗
- Website
- 1
- Posts per account
Reviews (17)
Ranked by views · Honest by design
Reviews are honest by design: positive, mixed, or critical. Positivity is never required.
I’m always looking for ways to spend less time switching tools and more time actually building. 👀 That’s why Rill Browser caught my attention. The ability to browse, research, and to debug then hand a page to Claude Code or Codex, is such a practical idea the information you find online can become the starting point for your next coding task. My biggest test is whether the agent gets enough context from the handoff to avoid extra explanations. One thing I’d improve: Show exactly what page content and context are passed to the agent. That’s the detail that could make this workflow genuinely useful. 🔗 http://rill.love
View on XJust checked out Rill browser and I think I get the idea. Basically, you browse as usual, but when you find something useful, you can pass it directly to Claude Code or Codex. Seems pretty handy for researching projects or figuring out how to fix something. Still curious how much context the agent actually gets from a page. Would be nice to see that before sending it.
View on XRill is a free Mac browser where Claude Code or Codex sit next to your tabs Runs on the plan you already pay for The flow: open any page, hit ⌘E, type the task Rill picks the project, the agent works in the background, you keep browsing Or hold Fn and just say it What I liked: passwords stay in your Mac Keychain, and the FAQ answers prompt injection and "can an agent buy something" upfront. Rare for an agent product What I'd improve: while it's "choosing a project" I want to see the pick and fix it before the agent starts, not after it touched the wrong repo Apple silicon, macOS 14+ rill.love
View on Xi explored Rill browser and i like the idea of connecting web browsing with AI agents. as someone who spends time researching projects, checking websites, and gathering ideas, being able to hand a page directly to Claude Code or Codex could make my workflow smoother. what worked: a practical way to connect research and building. what could improve: simpler onboarding for beginners who haven’t used these tools before. i’d love to see ready to use examples for research, debugging, and building. worth exploring for builders looking to work smarter. download and try it out on Apple Macs 🖥️ 🔗 rill.love
View on XRill makes it easy to connect browsing with AI coding agents. I love the background tasks and automatic project detection. You can delegate work and keep browsing while your agent gets things done. It's still evolving, and broader OS support would be a great addition.
View on XI’ve been testing Rill, a new browser where Claude Code & Codex live right beside your work It runs on your existing plan and genuinely understands your active projects I used it to debug a messy API integration Whenever i hit a wall, i just handed the open docs tab directly to the AI agent Skipping the copy-paste dance worked perfectly, AI reads the page and applies it to my code instantly But it occasionally struggles to parse heavy, JS-loaded pages quickly Devs, please add a hotkey to instantly send highlighted text to the agent without clicking
View on XRill is built around a useful idea which is turning whatever you’re reading in the browser into work for Claude Code or Codex, without constantly switching apps. From the product walkthrough, the strongest part is how it connects pages, existing projects and agent tasks in one place. One thing I’d improve is support for more agents, especially Cursor. That would make the workflow useful to a wider range of developers. I’d also want clear controls over what page context gets shared and when, particularly for tasks using logged-in sessions. The concept is compelling. The real test is how reliably it handles everyday work.
View on XRill is a Mac browser where Claude Code or Codex sit right beside you. It runs on the plan you already have and the browser itself is free, so there's nothing new to pay for What fits my workflow is not leaving the page. Browse for ideas or research, hit ⌘E, type the task, and the agent picks it up instead of me copy pasting between tabs. The tab groups are handy for research heavy sessions too What holds it back is reach. It's Apple silicon and macOS 14 or later only, so Intel Macs and Windows users are out One thing I'd improve is a quick preview of what context the agent gets before it runs rill.love
View on XTried Rill with my Codex workflow and I like how it keeps browsing + agent work in one place. I could research a page and hand the exact context to Codex without the usual copy-paste back and forth. What worked: the handoff felt fast and natural. What didn’t: I occasionally lost track of which page/context I had already sent. One thing I’d improve: a clearer history of pages handed to the agent. For research + building, this workflow makes a lot of sense.
View on XI like what @RillBrowser is trying to solve: the constant back-and-forth between what I’m researching and what I’m asking an AI agent to do. Being able to browse, keep multiple sources open, then hand a page or task to Claude Code or Codex without breaking that flow makes sense, especially for research-heavy work. Another nice touch is that Rill itself is free and works with the plan you already have. The biggest limitation is access. It’s currently limited to Apple-silicon Macs. I’d improve that with wider device support and a clearer first-time walkthrough for people new to agentic workflows. 🔗 rill.love
View on XI tried Rill browser and explored how it works with Claude Code and Codex. I like the idea of sending webpages straight to my AI coding agent without constantly switching apps. I’d love to see a smoother connection between the browser and the AI agent. Worth checking out!
View on XRill’s approach to AI-assisted browsing looks promising Connecting research across multiple tabs directly to Claude Code or Codex could make workflows smoother One limitation is its Apple silicon-only support,Adding Windows compatibility would make it accessible to more users
View on Xusually building with AI requires you to switch between tabs, Rill browser works differently with Rill you can directly interact with Claude or codex from any interface. I was able to simultaneously go through different webpages for ideas while still building with Claude, you only need to hit the CMD then type in your Idea. Rill directly ships it to Claude. for now Rill is only available for Mac, I wish there is a windows version but overall it's a scalable idea. here is the website https://rill.love/
View on XLess time switching tools, more time building. 👀 Rill Browser lets you browse, research, debug, then hand pages to Claude Code or Codex. One thing I’d improve: show exactly what page content and context gets passed to the agent. That could save extra explanations and make the workflow smoother. rill.love
View on XRill brings web browsing and AI coding agents into one workspace, making it easier to move between researching, debugging and building without constantly switching tools. One feature I particularly like is the ability to hand a webpage directly to Claude Code or Codex using ⌘E. It also supports comparing tabs and running agent tasks in the background while you continue browsing. Another plus is that it works with your existing Claude Code or Codex plan, so there's no additional subscription required. The limitations are that it's currently restricted to Apple silicon Macs. I'd like to see broader compatibility and improved extension support as Rill develops. https://rill.love/
View on XRill is a free browser for Apple Silicon Macs that runs on your existing Claude Code or Codex plan. No extra subscription needed. Browse, research, or build normally, then hit ⌘E on any page to hand it to your agent. It finds the right project, passes context, and the agent works in the background while you keep browsing. Supports tab comparison and voice too. What I liked: how natural it feels to turn any webpage into a task without switching apps or rewriting context. It fits right into the workflow. One thing to improve: Windows and mobile support. Currently Mac-only. Adding those would make it way more useful for everyone.
View on X