Agent S

Industry leading computer use agent and open sourced. Agent S is the only open-source solution among the top-performing agents. Empower your systems with this unique, powerful, and highly trusted tool.

Access code in GitHub

Blog

October 2, 2025

Latest Release

Agent S3: Approaching Human-level Computer Use with Wide Scaling

Since launching our first framework, Agent S, at 20.6% on OSWorld just a year ago, we’ve steadily advanced the frontier of computer-use agents. and now Agent S3 pushes performance to 69.9%, approaching human-level performance at 72%.

Read now

March 12, 2025

Second Generation

Agent S2: An Open, Modular, and Scalable Framework for Computer Use Agents

Our latest research pushes the boundaries of science, redefining what’s possible with computer use agents.

Read now

October 9, 2024

First generation

Agent S: An Open Agentic Framework that Uses Computers Like a Human

What are needed besides LLMs to build a better general agents across major operating systems.

Read now

Research Publication

Check below our publications.
The Unreasonable Effectiveness of Scaling Agents for Computer Use

Gonzalo Gonzalez-Pumariega∗, Vincent Tu∗, Chih-Lun Lee, Jiachen Yang, Ang Li, Xin Eric Wang

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

Saaket Agashe∗, Kyle Wong∗, Vincent Tu∗, Jiachen Yang, Ang Li, Xin Eric Wang

Agent S: An Open Agentic Framework that Uses Computers Like a Human

Saaket Agashe*, Jiuzhou Han*, Shuyu Gan, Jiachen Yang, Ang Li, Xin Eric Wang. 2024

PolicyCleanse: Backdoor Detection and Mitigation for Reinforcement Learning

Junfeng Guo, Ang Li, Lixu Wang, Cong Liu. CVPR 2023

Building an open-vocabulary video CLIP model with better architectures, optimization and data

Zuxuan Wu, Zejia Weng, Wujian Peng, Xitong Yang, Ang Li, Larry S. Davis, Yu-Gang Jiang. PAMI 2024

Forget but Recall: Incremental Latent Rectification in Continual Learning

Nghia D. Nguyen, Hieu Trung Nguyen, Ang Li, Hoang Pham, Viet Anh Nguyen, Khoa D. Doan. 2024