Rill Browser - The browser where Claude Code and Codex work beside you
Rill is an AI-native browser built around the Claude Code and Codex you already use. Browse normally, then press ⌘E on any page to turn what you're looking at into a task for your agent. Rill finds the right project, passes along the context, and the agent works while you keep browsing. It also sorts your tabs into themes, turns your history into days you can search, and brings every project your agents are working on into one place. Free, on the plan you already have.


p/reso
p/dex-by-exmergo
p/runevr
p/producthunt
p/google-cloud-platform
p/ai-context-flow
p/seshka
p/kodlo
p/duckfightclub
p/talanoa-2
p/nudgeforme
p/nexupira
p/many-displays
p/murror
p/operum
p/dino-kids
p/tabstack
p/rithub
Replies
the per-turn snapshot and Undo you mentioned in another thread is the detail that got me, I've been asking a version of this question on a few launches lately - does that snapshot/undo only cover the git state, or does it also know about anything the agent did outside the repo during that turn (an API call it made, a form it submitted on the page it was reading)? code is easy to revert, a request that already fired isn't, and that gap is the part I haven't seen anyone solve yet
@galdayan it knows everything the agent knows through that turn. due to practical reason we can't save every turn that ever happened, but all recent turns will have a good snapshot
@williamgaoharvard good to know, thanks. recent-turns-only makes sense as a practical tradeoff, that covers the case I actually care about day to day anyway
@galdayan glad it covers! Feel free to suggest more features as you use Rill. We're always iterating
Turning the page you are already looking at into a task for your agent with one shortcut is a really natural way to blend browsing and building. Passing along the right project context is the part that usually goes wrong in these setups, so handling that automatically is nice. Does the agent stay in the background while you keep browsing other tabs?
@karimbenkeroum Yes. The key idea is that you send the request the moment you got an idea, and once you sent the request you don't need to do anything else. You can browse this tab, other tabs, close any tabs, or even close Rill and come back later. Agents will continue working on the background
sending an idea straight from the page makes sense. does the task keep a snapshot of that page, so the agent still has the original context if i navigate away or the site changes?
@jeetendra_kumar2 The agent has original context. So once you sent your ask, you can keep browsing as you always do - jump through tabs, close tabs, etc
Congrats on the launch, William! The code-switching problem is real. Ideas tend to hit when I'm reading something unrelated, and having ⌘E turn the page into a task for the agent in the right project sounds like a great way to catch them. Looking forward to trying it out.
@adityaharish2002 Thank you! Please do give it a try and share any feedback you have
The idea of turning a random thought while browsing into actual work without breaking your focus feels genuinely useful.Congrats @williamgaoharvard
@angelo_bram Thank you! So much innovation and productivity can come when we treat our random thoughts seriously
I use Codex for research too, so I can see this being useful beyond coding. Being able to trace a draft back to the pages that informed it would matter more to me than just handing over the tabs.
@znu Great to know! Research is one of the areas I've been designing it for, so that I don't need to leave the paper when ideas struck but I'm half way reading it. What do you mean by tracing a draft back?
I’d love to queue up a few tasks at night and wake up to them done. Is anyone already using it like that?
@irving_ai I definitely am! Super satisfying to know that agents are doing great works when I'm asleep. Codex and Claude Code can already make that happen but Rill can make that happen even more. You should try it!
Smart browser design. Questions: Does it handle multiple Claude projects simultaneously? Privacy model for context sharing? Keyboard shortcut customization for power users? API access for agent integration?