I love when numbers go up 🌊 AI Agent Researcher @openhandsdev 🤖

Joined March 2025
日経ソフトウエア 2026年3月号 雑誌 – 2026/1/23 amzn.to/3Z1Oxnv amazon #ad AI エディタ入門 Visual Studio Code GitHub Copilot プログラミング向け AIエージェント OpenHands 自然言語でアプリを作る 生成AIコーディング道場
1
3
345
Juan Michelini retweeted
What do these tasks have in common? - Fixing security vulnerabilities - Data entry from messy unstructured forms - Version upgrades They're repetitive but important tasks that can be solved in a few lines of code by our new OpenHands Software Agent SDK.
1
7
2
18
6,604
3/ This week we are proud to announce our latest eval with the latest version of @allhands_ai's OpenHands and GPT-5. Remarkably, GPT-5 increased the SOTA on SWT-Verified by 15%, taking 1st, and GPT-5-mini took a well deserved 3rd spot. 🏅
1
1
1
125
Juan Michelini retweeted
A lot of agents out there are over-optimizing for SWE-bench. We've been very careful to ensure OpenHands generalizes to a wide variety of eng-related tasks Great to see that work pay off as we hit #1 on SWT-Bench!🏆
Having appropriate tests makes a world of difference for agent-driven development. If your agent can write a test to localize a bug or exercise a new feature, the following implementation is much more solid. OpenHands+GPT-5 is now 🥇 on the SWT-Bench testing leaderboard!
2
17
1,766
OpenHands is 🥇 place on the SWTBench the unit test benchmark. Great team, great product, and the benchmarks prove it!
Having appropriate tests makes a world of difference for agent-driven development. If your agent can write a test to localize a bug or exercise a new feature, the following implementation is much more solid. OpenHands+GPT-5 is now 🥇 on the SWT-Bench testing leaderboard!
3
249
Juan Michelini retweeted
Having appropriate tests makes a world of difference for agent-driven development. If your agent can write a test to localize a bug or exercise a new feature, the following implementation is much more solid. OpenHands+GPT-5 is now 🥇 on the SWT-Bench testing leaderboard!
6
18
6
100
22,264
Juan Michelini retweeted
We evaluated GPT-5 in OpenHands and it's the new number one coding agent model for us! Using exactly the same tools and harness it's 1.4 points better than Claude Sonnet 4 at 60% of the price. Full results here: docs.google.com/spreadsheets…
16
30
8
240
32,451
Juan Michelini retweeted
Introducing the OpenHands CLI, a new coding CLI that: - Has top accuracy (similar to Claude Code) - Is completely open source, MIT licensed - Is model agnostic, use an API or bring your own - Is simple to install and run `pip install openhands-ai` and `openhands` (no Docker!)
37
259
62
1,977
309,340
Juan Michelini retweeted
I am very excited about both the accuracy results and just my feeling playing around with this new agent. The ability to research things online and comprehend a wide variety of multimodal content has removed many of my blockers in using agents in my everyday work.
What if we could have *trustworthy* agents that don't just write code, but also do research, understand multimodal content, and perform many practically useful tasks? Today at OpenHands, we released a new agent that gets SOTA or competitive performance on 8 diverse tasks.
4
11
87
7,707