computer-using-agent

There are 1 repository under computer-using-agent topic.

• a-real-ai / pywinassistant

  The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visualization-of-Thought and Chain-of-Thought reasoning to elicit spatial reasoning and perception, emulates, plans and simulates synthetic HID interactions.

  artificial-general-intelligenceartificial-intelligence-algorithmscotvotartificial-narrow-intelligenceuiui-uxuxcuacomputer-using-agentgraphical-user-interface
  Language:Python 1311

• OS-Agent-Survey / OS-Agent-Survey

  This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use".

  mllmssurveyagentllmsguigui-agentcomputer-usephone-usebrowser-agentweb-agentos-agentcomputing-devicesos-agent-surveycomputer-using-agentcomputer-usingoperator
  238

• reidbarber / webmarker

  Mark web pages for use with vision-language models

  claudecomputer-usecomputer-using-agentcuageminigpt4ogpt4vllmsoperatorplaywrightpromptprompt-engineeringqwen-vlset-of-marksomvision-language-model
  Language:TypeScript 44

• ercbot / valk

  Simple, observable computer use - Remote desktop for AI agents

  aicomputer-usecomputer-using-agentpython
  Language:Rust 3

• thethinkmachine / 4o-agent

  A ReAct Principles based fully autonomous Command Line Computer Using Agent

  agentic-aicomputer-using-agentfastapigpt-4olangchainlinuxllm-agentlocalservershell
  Language:Python 0

• Mihonarium / food_ordering_agent

  Use an LLM agent to automate ordering food and other items from Deliveroo, Uber Eats, DoorDash, etc.

  agent-basedagentsamazonapiassistantassistant-chat-botsassistants-apicomputer-usecomputer-using-agentcomputerusedeliveroodoordashhome-assistantllmllm-agentsubereats
  Language:Python