
Agent S is an open-source AI agent framework that controls ordinary desktop and web applications through the screen, mouse and keyboard. It runs on macOS, Windows and Linux and is aimed at developers, computer-use researchers and people building automation for their own desktops. You describe the task in natural language; the agent clicks, types and scrolls without requiring an API integration or a separate script for each application.
The Python framework separates the model that reasons about a task from the grounding model that identifies where to act on screen. It supports OpenAI, Azure OpenAI, Anthropic, Gemini and OpenRouter, along with vLLM inference for open-weight models. UI-TARS-1.5-7B is the recommended grounding model. Desktop control runs on your computer, while cloud model providers require an internet connection. The agent is designed for a single monitor.
An optional local coding environment lets the agent execute Python and Bash for work that's better handled in code, such as processing spreadsheets, organizing files or editing documents. That code runs on your machine with your user permissions. Agent S uses the Apache 2.0 license, so developers can inspect and adapt the framework.
Claim this page with an email at simular.ai. Agent S gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Agent S?Promote it
Something wrong or outdated on this page?
10.3KUpdated 1 year agoMIT
macOS · Windows · Linux#Multimodal input#Ollama integration
Self-Operating Computer lets a vision-capable AI model control a desktop by reading the screen and choosing mouse and keyboard actions to carry out a goal. It's a Python framework for developers and researchers exploring AI agents that work through application interfaces. The code uses the MIT license.
116.8KUpdated 4 days agoMIT
#MCP#Ollama integration#Structured output
6.4KUpdated 2 years agoApache-2.0
Web · Browser Extension#Code execution
LaVague is a Python framework for developers building AI agents that carry out tasks in a web browser. An agent takes a plain-language objective, examines the current page, and generates and executes browser actions across multiple steps. It's open source under the Apache 2.0 license.
10.5KUpdated 7 months agoApache-2.0
macOS · Windows · Linux · Android · Web#Code execution#MCP#Multimodal input
7.7KUpdated 5 days agoMIT
macOS · Windows · Linux · Docker · Web#Code execution#GGUF#Hugging Face integration
3.1KUpdated 2 days agoApache-2.0
macOS · Windows · Linux · Web#Code execution#MCP#Multi-agent workflows
Browser Use is an MIT licensed browser agent for developers who want AI to carry out tasks on websites. You can run the open source agent on your own machine from Python, choose a model, and use either a local or cloud browser. A CLI is available for browser tasks too.
aichat brings Ollama and cloud AI services into the same terminal interface for developers and people who work at the command line. It runs locally on macOS, Linux and Windows, with Android support through Termux. Model processing happens through the backend you choose: Ollama supports local models, while providers such as OpenAI, Claude and Gemini process requests in the cloud.
mistral.rs is an open source inference engine for running models on your own computer or self-hosted server. It's for developers building AI applications and people who want local chat, multimodal models and agent tools in the same runtime. The Rust project uses the MIT license.
BotSharp is a self-hosted framework for .NET developers building AI agents into business applications. Written in C#, it runs on Windows, Linux and macOS and is open source software under Apache 2.0. Its plugin design lets teams choose their model provider, storage and interface while keeping agent coordination in the same framework.