@enesonus

Founding Engineer @limrun

 Istanbul,Turkey
enesonus.com
Joined September 2023
  • Tweets131
  • Following106
  • Followers94
7Media
Try @limrun on e2e and LMK if you have any cloud service close to its performance
Oskar
@o_kwasniewskiOct 12
Replying to @o_kwasniewski
we also shipped e2e v0.20.0 ⚡ → e2e run --watch → @limrun integration → Improvements to decision executor
1
3
155
I will give 1k limrun credits out of my pocket if you can btw
22
Plugin extensions are so cool 😎 Building a native iOS app with Codex + Limrun. Build → try → annotate → iterate. All in one place. Feels like it’s part of Codex.
1
7
3
39
419,571
Limrun is just a plugin away from you 🚀
hasan türken
@turkenhOct 1
Plugin extensions are so cool 😎 Building a native iOS app with Codex + Limrun. Build → try → annotate → iterate. All in one place. Feels like it’s part of Codex.
6
140
Future is the cloud agents
ClaudeDevs
@ClaudeDevsSep 23
Cloud sessions are officially available and out of research preview! They let you keep Claude Code working, even when your laptop is closed. Existing subscribers get a one-time credit to try them: $100 on Pro, $250 on Max.
1
72
Just run `lim skills install` and have your cloud agents use the iPhone Duo in 3D with Limrun or make it integrate it to your system with our React component 👨‍🍳
lim.run (YC P26)
@limrunSep 23
Shape matters, too. iPhone Duo support and the new 3D view are available to use in our console and you can embed it in your web application with a single React component!

90
Workin on duo view 👀
1
6
872
cooking iPhone Duo👨‍🍳 @limrun
3
1
2
14
2,575
Limrun easily converts any AI agent to a mobile dev factory
hasan türken
@turkenhAug 20
Grok @bot can run a mobile dev factory with @limrun.
2
237
I dont know about AGI but limrun is HERE If you want to ramp up your AI Mobile dev game send a DM!
muvaf
@muvaffMay 21
We couldn't hold it any longer! If you have a mobile app, we should talk. If you built software factories, we should ABSOLUTELY talk!!
1
3
1,406
Limrun (@limrun) provides the infrastructure to leverage your favorite cloud agents for mobile development too. Today, we provide remote XCode, IOS & Android Simulators to Replit, Rork, Momentic AI, and many more. Congrats on the launch, @muvaff! ycombinator.com/launches/QSu…
26
16
6
104
307,219
Enes retweeted
muvaf
@muvaffMay 21
We couldn't hold it any longer! If you have a mobile app, we should talk. If you built software factories, we should ABSOLUTELY talk!!
Y Combinator
@ycombinatorMay 21
Limrun (@limrun) provides the infrastructure to leverage your favorite cloud agents for mobile development too. Today, we provide remote XCode, IOS & Android Simulators to Replit, Rork, Momentic AI, and many more. Congrats on the launch, @muvaff! ycombinator.com/launches/QSu…
7
7
1
57
275,769
Imagine netflix introduces a service where you can talk with your favorite movie characters in realtime with the help of AI. Talking with Elliot would be cool btw
616
The biggest customer consistency advantage for chatbots is a well designed "Personalization" IMO. If an LLM knows what I prefer and how to tackle problems in a way that suits my lifestyle, it is much more valuable than a fraction of higher intelligence
511
Sometimes I consult to an AI model for an implementation idea and it gives very valid opinions. Having someone instantly give you some feedback and look at the problem from a different angle is a very nice productivity multiplier
362
Weird behavior from Gemini 3 Pro at Cursor 🧐 I wanted an "Implementation Plan" from the model so that I can review the code but it seems that Gemini 3 Pro likes the "indie mode". It reviews it's own code and approves all by himself 😄
1
840
3D printing is the best hobby a developer can have imo
1
532
If you want to reduce your LLM costs first thing you should look at is output length. Output token costs are 4-8x of input costs
2
494
I hate to say but gpt-4o-mini > gpt-5-nano and mini for tool calls. It is faster it is cheaper and more reliable
1
1
390
Small GPT 5 models use additional output tokens due to reasoning and if you set the reasoning effort to “minimal” they are not reliable. Output tokens are more expensive than input (generally 5-6x) and because of that gpt 5 nano gets more expensive than 4o mini
1
300
Load more