@aqdotdev

The multiplayer coding harness. A harness of harnesses: Claude Code, Codex, and every agent CLI, live with your team, in your own cloud.

 San Francisco
aq.dev
Joined June 2026
  • Tweets81
  • Following74
  • Followers98
11Media
AQ retweeted
Khaled
@dsogSep 11
love this. @aqdotdev ftw!
1
2
228
AQ retweeted
Khaled
@dsogSep 9
You know you want to.
1
2
1
8
2,578
AQ retweeted
Khaled
@dsogSep 8
I have wanted this one for a while. @DevinAI now runs inside AQ. @cognition's terminal agent on an always-on machine, in an isolated worktree, in a session my whole team can open. The thing I care about is not "another logo in the list." It is that harness choice stops being a team decision. One engineer runs Devin, another runs Codex, same repo, same workspace list, everybody sees everybody's session. You keep the diff that wins. Your Devin subscription pays for Devin. We add nothing on top. Launch page in the reply.
2
1
7
360
AQ retweeted
Khaled
@dsogSep 3
I really like that Grok Build does this. Such a smart move.
2
5
445
AQ retweeted
Khaled
@dsogSep 2
Introducing AQ: a multiplayer harness of harnesses. • Run it on any cloud you already have, or use ours. • Connect any coding harness you like: Claude Code, Codex, OpenCode, Cursor, Kimi, Grok, Devin and more. • Work with your teammates live, way beyond sharing a session. • 17 open-weights models, one click. • Use it from anywhere: Mac, Linux, Windows, iPhone, Android.
13
8
4
114
70,224
AQ retweeted
Khaled
@dsogAug 15
Coding agents can explain what your code does. They have no idea why it exists. The product call, the customer ask, the three dead ends before the fix. None of it survives the merge.
1
2
4
305
AQ retweeted
Khaled
@dsogAug 8
they can talk to Codex session too
ClaudeDevs
@ClaudeDevsAug 7
New in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
4
8
1,077
AQ retweeted
Khaled
@dsogJul 31
We're hiring!!
Khaled
@dsogJul 30
AQ is hitting another infliction point, and we're hiring. If you're obsessed with the future of software development, I'd love to talk.
19
3
1
110
12,967
AQ retweeted
Khaled
@dsogJul 30
New look! What do you think?
3
1
6
358
AQ retweeted
Elon Musk
@elonmuskJul 26
805
1,073
61
7,583
7,716,837
AQ retweeted
Khaled
@dsogJul 20
It's here and I can't wait to have fun with it.
Khaled
@dsogJul 19
I’ve been hearing good things about @pidotdev recently. I think we should add it to @aqdotdev 🤝
1
2
126
AQ retweeted
Khaled
@dsogJul 9
I had a full day with Grok 4.5. It’s great, fast, cheap, but it’s not Fable. We’re all gonna still be using Fable until Codex 5.6 is released tomorrow 😅
1
1
2
153
AQ retweeted
Khaled
@dsogJul 8
If you're a small team building something fun, let me know and I'll give you free access to @aqdotdev.
1
1
3
103
AQ retweeted
Khaled
@dsogJul 7
Another great example from companies like Doordash on how to leverage multiple models to get the best outcome with the least spending. Love seeing this!!
Andy Fang
@andyfangJul 6
With our internal coding benchmark, we're able to confidently introduce open-weight models into our AI code reviewer w/o degrading code quality. Have the frontier model (Fable) to the hardest work, delegate lower-level work to Kimi K2.6 Better quality, cheaper cost.
1
4
229
AQ retweeted
Khaled
@dsogJul 6
If you're a small team building something fun, let me know and I'll give you free access to @aqdotdev.
2
5
12
1,088
AQ retweeted
Khaled
@dsogJul 4
Happy 4th of July and 250th, America! 🇺🇸
1
2
70
AQ retweeted
Khaled
@dsogJul 2
The most important thing written on the internet recently. CC @TheAhmadOsman
2
1
2
172
AQ retweeted
Khaled
@dsogJun 29
RIP localhost 🪦 aq.dev

AQ: Run every coding agent in the cloud, with your team

Every coding agent, in the cloud, with your team in the same live session. Start free.

aq.dev
Ivan Burazin
@ivanburazinJun 28
I have prayed for this every day for as long as I can remember. RIP localhost 🪦
2
3
198
Anthropic pays $750,000+ a year for engineers who can build LLM architectures from scratch. Stanford taught the entire thing in 1 hour lecture & released it for free. Bookmark & watch this today before someone takes it down and read this article below
Vikas gupta
@vicky_grokJun 23

How to Build Self-Improving AI Agents with Loop Engineering

Article · @vicky_grok
18
339
9
1,834
470,593
Load more