OpenAdaptAI @OpenAdaptAI

Open source AI that automates tasks in desktop apps by observing human demonstrations. Mac/Win compatible. https://t.co/7BQASEeo82 openadapt.ai Joined May 2023

Tweets

68
Followers

418
Following

0
Likes

119

Xinyuan Wang @xywang626

2 months ago

We are super excited to release OpenCUA — the first from 0 to 1 computer-use agent foundation model framework and open-source SOTA model OpenCUA-32B, matching top proprietary models on OSWorld-Verified, with full infrastructure and data. 🔗 [Paper] arxiv.org/abs/2508.09123 📌…

14 99 462 136K 253

Download Image

Xinyuan Wang @xywang626

2 months ago

🙌 Acknowledgement: We thank @ysu_nlp, @CaimingXiong , and the anonymous reviewers for their insightful discussions and valuable feedback. We are grateful to Moonshot AI for providing training infrastructure and annotated data. We also sincerely appreciate Jin Zhang, Hao Yang,…

0 3 19 1K 3

Rico Pagliuca @pagilgukey

6 months ago

Anybody looking for a GUI+ICL-->MCP library should definitely check out OmniMCP which puts Microsoft's Omniparser to use in generating GUI tool use APIs. Early days but pretty neat omnimcp.openadapt.ai

1 2 4 219 1

Python Hub @PythonHub

a year ago

OpenAdapt AI-First Process Automation with Large Multimodal Models (LMMs). github.com/OpenAdaptAI/Op…

0 4 16 2K 1

Richard Abrich @abrichr

8 months ago

I prompted @OpenAI's ChatGPT o3-mini-high and @deepseek's R1 to implement code to for deploying @Alibaba_Qwen's Qwen2.5-VL. Both agree that R1's implementation is "more comprehensive" and better "for production systems".

1 1 7 723 0

Download Image

Richard Abrich @abrichr

8 months ago

Qwen2.5-VL is the first open source multimodal model that appears to be able to accurately generate bounding box coordinates 🚀 Thank you @Alibaba_Qwen ! Excited to integrate this in @OpenAdaptAI x.com/Alibaba_Qwen/s…

Qwen @Alibaba_Qwen

8 months ago

2 5 56 13K 21

Download Image

1 2 9 2K 4

Download Image

Yujia Qin @TsingYoga

8 months ago

Check out our latest GUI Agent -> UI-TARS 🥳 A vision-language model surpasses GPT-4o & Claude Computer-Use Paper, code, model ckpt, desktop APP are now open-sourced~ github.com/bytedance/UI-T… github.com/bytedance/UI-T…

10 40 189 37K 115

Download Image

Richard Abrich @abrichr

8 months ago

github.com/MoonshotAI/Kim… > 🚀 Introducing Kimi k1.5 --- an o1-level multi-modal model 🤯

1 1 2 261 0

Richard Abrich @abrichr

8 months ago

github.com/deepseek-ai/De… > DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. huggingface.co/deepseek-ai/De… We can run frontier models at home now.

1 2 6 586 1

Richard Abrich @abrichr

9 months ago

Another day, another breakthrough: Apply DCT to convert actions into frequency components, quantize them prioritizing low frequencies, then use autoregressive prediction in frequency order (low to high) to generate actions. From @physical_int. May generalize to @OpenAdaptAI.

1 1 7 326 2

Download Image

Richard Abrich @abrichr

9 months ago

@hwchase17 With @OpenAdaptAI you start and stop recording demonstrations of repetitive tasks via the tray icon. Show, don't tell. Perform, don't prompt.

0 1 3 241 0

Richard Abrich @abrichr

9 months ago

Nice taxonomy of Agents from @huggingface smolagents

0 1 3 251 1

Download Image

Richard Abrich @abrichr

11 months ago

@JosvdWest @OpenAdaptAI Sure does! Mac and Win compatible.

1 1 3 205 1

Download Image

Richard Abrich @abrichr

11 months ago

@OpenAdaptAI @julien_c @Microsoft @AWS @Docker (venv) % python client.py http://34.206.53.77:7861 ~/Desktop/screenshot.png Loaded as API: http://34.206.53.77:7861/ ✔ Parsed content: ... 2024-10-29 11:13:07.414 | INFO | __main__:predict:84 - Output image saved to: output_image.png

3 1 2 193 0

Download Image

Richard Abrich @abrichr

11 months ago

@julien_c Deploy @Microsoft OmniParser to @AWS #EC2 automatically via @Docker and #GitHub actions: github.com/microsoft/Omni…

1 3 7 277 2

louis030195 @louis030195

11 months ago

within the next year, AI will be able to ingest everything that ever happened on your computer check out this cool video about tools enabling this: @OpenAdaptAI @tooluseai @MikeBirdTech @OpenInterpreter @FieroTy @abrichr and @screen_pipe :) youtube.com/watch?v=VgJ0Cg…

3 3 12 17K 3

Julien Chaumond @julien_c

11 months ago

If I was starting a company today, I would look into productizing this model 👀

merve @mervenoyann

11 months ago

If I was starting a company today, I would look into productizing this model 👀

30 385 3K 472K 4K

Download Video

14 86 1K 164K 1K

Tool Use @ToolUsePodcast

11 months ago

Automate your desktop for free with @OpenAdaptAI @abrichr joined us this week to share his open source tool that saved one user $75,000

1 3 13 3K 3

Download Video

Richard Abrich @abrichr

12 months ago

Screenshot from youtube.com/watch?v=01g_Ef…. One way to think about @OpenAdaptAI is as a way to learn "Flows" automatically by observing human demonstrations.

2 2 9 347 7

Download Image

Andrej Karpathy @karpathy

a year ago

It's a bit sad and confusing that LLMs ("Large Language Models") have little to do with language; It's just historical. They are highly general purpose technology for statistical modeling of token streams. A better name would be Autoregressive Transformers or something. They…