Same (@samedotdev) header
Same (@samedotdev) profile picture

if you can dream it, same can build it - https://nitter.cf/t.co/ikJcZ7yb0b

Joined January 2025
Photo by Same (@samedotdev)Photo by Same (@samedotdev)Photo by Same (@samedotdev)Photo by Same (@samedotdev)Photo by Same (@samedotdev)Photo by Same (@samedotdev)Photo by Same (@samedotdev)Photo by Same (@samedotdev)Photo by Same (@samedotdev)
We just launched React Grab. ...AND it's 100% free and open source to contribute, fork, hack, whatever you want Free to use inside of @samedotdev too!
Introducing React Grab: Select elements and edit with Cursor/Claude Code Works in your localhost and in any React app
1
12
5,943
Apex ranks #5 on ReactBench Very cost-efficient model for writing React + app code
We trained Apex for React Native. It landed #2 at fixing web React. Callstack's Apex is tied #5 overall on @aidenybai's ReactBench. React Native tuning carries over to the web. Try it on Vercel AI Gateway or apex.callstack.com
6
8
1
48
5,034
dont sleep on this agent skill
Introducing /improve-threejs Turn vibe-slop Three.js prototypes into stunning apps It makes slow, visually buggy games run fast!
1
1,105
Introducing /improve-threejs Turn vibe-slop Three.js prototypes into stunning apps It makes slow, visually buggy games run fast!
54
112
14
2,153
111,693
Grok 4.6 is exceptional at fixing React code It ranks #2 on ReactBench:
29
19
3
724
45,828
Opus 5 is the best Claude model on ReactBench Better at frontend code than Claude Fable 5 and >2x cheaper (!!)
22
10
1
410
48,107
Kimi K3 ranks #6 on ReactBench - It performs better than Opus 4.8 while being over 2x cheaper (!!) - Scores 33%, jump of +10% compared to K2.7 - Lags behind the frontier (Fable and Sol) in frontend production-readiness:
41
23
7
544
76,055
Introducing ReactBench A benchmark for coding agents on real React work Models write bad React code - useEffect, slow performance, memory leaks
112
123
45
2,127
343,564
We've spent the last 3 weeks finding which is the best model at frontend: 1. GPT 5.6 Sol 2. Fable 5 3. GPT 5.6 Terra
Introducing ReactBench A benchmark for coding agents on real React work Models write bad React code - useEffect, slow performance, memory leaks
9
987
Introducing React Doctor for Performance Fix slow React code and make it fast npx react-doctor@latest
42
77
16
1,638
156,642
Introducing React Security Doctor Fix security exploits in your React app Run as CLI. Fully open source npx react-doctor@latest
21
62
6
726
52,352
New in React Doctor: Prevent bad React code from breaking prod Install GitHub Action. Fully open source npx react-doctor@latest
17
64
5
888
63,391
Introducing React Native Doctor Find performance and security bugs in your mobile app Run via CLI and fix with agents. Fully open source npx react-doctor@latest
93
133
16
1,828
172,750
Introducing /react-doctor Your React app probably has bad code. This fixes it Install as agent skill. Fully open source. npx react-doctor@latest
134
345
42
5,882
587,357
Introducing React​ Review Agents write terrible React, this helps you fix it Just paste your GitHub repo! No signup required
63
97
16
1,749
156,292
React Doctor v2 is here Your agent writes bad React code, this catches it Works with Next.js, Vite, React Native. Fix your app in minutes npx react-doctor@latest
130
350
50
5,145
788,285
Introducing Expect Test your agent code in a real browser Works with your agent. Fully open source
30
38
9
804
73,764
Introducing Expect Let agents test your code in a real browser 1. Run Claude Code / Codex to QA your app 2. Watch a video of every bug found 3. Fix and repeat until passing Run as a CLI or agent skill. Fully open source
227
302
59
4,518
847,571
Introducing React Grab Select any element on your page → tell Claude Code or Codex what to change Fully open source npx react-grab@latest
250
436
67
7,742
960,447
Introducing React Doctor Scan your React codebase for anti-patterns: - Unnecessary useEffects - Fix accessibility issues - Prop drilling instead of context / composition Run as a CLI or agent skill. Repeat until passing. Fully open source
345
750
131
10,362
1,082,308
we've been cooking something new :) go check it out
We built the fastest coding agent for frontend This video is NOT sped up Comment "ami" for 100k free tokens
1
6
1,479