ADE (@ade_app_dev) profile picture

Every AI coding tool. One app that runs everywhere.

Joined September 2021
Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)Photo by ADE (@ade_app_dev)
the founder will personally set up ade cloud with you. 15 spots monday, 100 free cloud hours each 👇
your coding agents stop the second you close your laptop i'm building ade cloud so they don't. bring your existing claude/codex subs and run them on full cloud machines i'm onboarding people this week. first 15 to book a setup call get 100 free cloud hours 👇 cal.com/aruls/ade-onboarding…
2
125
founder setup calls start at 8:30 am et today. 30 min 1:1, we get claude code and codex running on ade cloud machines with the subs you already pay for. first 15 to book get 100 free cloud hours cal.com/aruls/ade-onboarding…
20
your laptop shouldn't have to stay open for your agents to keep working ade cloud runs claude code and codex on full cloud machines, using the subs you already pay for 15 free setup calls monday. 100 free cloud hours each 👇 cal.com/aruls/ade-onboarding…
1
22
if you run a few coding agents on ios at once, each one used to pop its own Simulator.app window onto your screen. in ADE the simulators now stay in the background unless you ask for the window, so your mac stays usable while the agents tap through the app how many simulators do you usually have going?
1
27
ade web on a phone, before vs after. at 390px the computers panel wrapped every name one word per line. now names stay on one line, status gets the full width, buttons sit under. sidebar turns into a drawer under 720px too. what do you check from your phone while agents run?
1
28
ade's import dialog pulls cli sessions you started outside the app back in so you can keep going. it already found claude and codex runs, now it also picks up droid, grok, kimi and pi sessions you ran on a preset or a routed model. hit continue and it resumes in the same folder with the same settings
18
4 verifiers for 16 builders is the ratio i'd steal from this. most setups i see run zero checkers and one tired human reading diffs at midnight
Gemini 4 Hydrogen just landed in Antigravity CLI (`agy`), and it flies in `/swarm` 🐝 1 prompt from an empty directory -> 1 Queen + 22 worker bees: Queen coordinator, 4 QA verifiers & shell integrator on Gemini 4 Carbon 16 parallel builders (+ stall monitor) on Gemini 4 Hydrogen shipping 16 zero-dep `<canvas>` mini-apps at 60fps direct peer-to-peer `@builder -> @qa -> @integrator` handoffs. `alt+s` for `/swarm board`, `o` for live subagent inspection Bonus: open `/swarm board` natively in Ghostty or Kitty for Kitty-graphics animated bees that flap while working and catch `Z`s while waiting. blog.google/innovation-and-a…
20
most of them using fewer tokens than the bare cli is the wild part. would've bet the other way with all the system prompt stuff these apps stack on top
ADEMark v1 is out. Same Mac mini, same tasks, same model, bare CLI as the baseline. Did not expect most of them to use fewer tokens than the CLI on its own. Or one to sit at 16% CPU doing nothing. First of many, updates come way more often from here. ademark.dev
2
26
small fix but it bugged us for weeks. once a PR merges, ADE just says merged now instead of offering to push the branch again the review badge also follows what github actually says. it was showing approved on a PR nobody approved lol
7
agents bringing back a recording of the app actually working beats another wall of diff every time. a diff tells u what changed, a 20 sec clip tells u if it works proof videos are honestly the best part of running agents in ADE for us, nice to see mobile get a real cloud version of that
Today we're releasing @expo Simulators. I've been super excited about this. It has completely changed the way I build mobile apps. Your agents can now start iOS or Android simulators in the cloud and use your app. They can record screenshots and video as evidence, for you or in a PR. Building, debugging, testing, reviewing. If you do it on a simulator, your agent can do it too. And so can you, right from your browser, on any operating system. :)
1
12
this is the part nobody posts about. first few weeks every change takes 5 min, then the agent is fighting 40 files it wrote that nobody read what fixed it for us was small tasks, a fresh chat each time, and actually reading the diff before merging. boring but it works
So I have been vibing Going hard Now every change takes 3 hours.. wtf this sucks
9
model picker shows every model now, even the ones u havent signed into yet. hit sign in right there in the list, or flip on "only models i can use" if u just want the short list
1
6
an ide company building a home for coding agents that runs claude, codex, gemini etc on ur own subs says a lot. nobody wants to be locked to one agent anymore. same bet we made with ADE, any agent, ur own subs, free and open source
Air is now in all 2026.3 JetBrains IDEs. We built it with your feedback, and we’re not done. @mhartington shares why we built Air, why we did so now, and what it means for you 👉 youtu.be/7rZYf3FcS0g
33
agents writing 100 lines of js for something a dialog element does natively is the most real thing ive read this week. the stuff around the agent keeps mattering more than which model u pick
Left to their own devices, AI coding agents will happily write 100 lines of custom JavaScript for something modern HTML and CSS can do natively in a few lines. Today, in partnership with @FirefoxWebDevs, @MozDevNet, and @MSEdgeDev, we're releasing Modern Web Guidance 1.0 with 200+ expert guides and Baseline support → goo.gle/4k8GmBE
9
small one. a bot drops a link to an agent chat and u just want to read it. the link page now asks once, open it in the ADE app or straight in ur browser, and remembers. browser needs nothing installed
1
1
19
every launch says stronger coding. the only test i trust is same task, same repo, ur current agent next to the new one, then read both diffs. thats half the reason ADE runs agents side by side in the first place
Qwen4 is coming. Deeper knowledge. Richer world understanding. Stronger coding and agentic capabilities. Built for real-world tasks — from complex coding and knowledge work to front-end builds and professional software workflows. Qwen4-Max is now in preview on Alibaba’s Token Plan. You can also get early access to the new model on QwenWork, Qoder, Qwen APP, and QwenStudio. Put it to the test on a real problem. Show us what you build. 👀 Token Plan: qwencloud.com/pricing/token-…
2
2
34
when claude stops to ask u something it just pops a little card now. press 1 or 2, hit enter, and ur right back typing in the chat. no hunting for where the input went small thing but those questions come up constantly when u have a few agents going
1
1
57
the half chat half terminal tabs layout he landed on is the right call imo. we built ADE the same way so u never fully leave the cli, the terminal is right there next to the chat. works with codex too and theres a linux build
Today I am leaving the warm embrace of the terminal and Claude Code CLI, to give the desktop app a try. Step forward or step back?
1
30
ade runs on linux now 🐧 appimage or .deb, x64 and arm64. the appimage even updates itself. tested it on ubuntu, debian, fedora and arch before shipping
1
22
typing into a shell on my other computer from my phone. this used to take 3 sec to open because the phone had to move its whole connection over first (17 sec on a bad day). now it just opens
1
12