web-infra-dev / midsceneLinks
Driving all platforms UI automation with vision-based model
β11,532Updated this week
Alternatives and similar repositories for midscene
Users that are interested in midscene are comparing it to the libraries listed below
Sorting:
- Pioneering Automated GUI Interaction with Native Agentsβ9,343Updated last week
- π₯οΈ Run AI Agent in your browser.β15,562Updated 5 months ago
- The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infraβ27,325Updated 3 weeks ago
- Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Oβ¦β12,162Updated 2 months ago
- Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More πβ5,210Updated last month
- Agent S: an open agentic framework that uses computers like a humanβ9,671Updated 2 weeks ago
- The AI Browser Automation Frameworkβ20,833Updated this week
- 5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base andβ¦β5,011Updated 2 weeks ago
- A simple screen parsing tool towards pure vision based GUI agentβ24,344Updated 4 months ago
- Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural lβ¦β3,824Updated 8 months ago
- Monitor browser logs directly from Cursor and other MCP compatible IDEs.β7,058Updated 10 months ago
- FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build β¦β7,674Updated 2 weeks ago
- Kortix β build, manage and train AI Agents.β19,325Updated this week
- The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot π¦Β· β¦β6,486Updated this week
- π Make websites accessible for AI agents. Automate tasks online with ease.β77,901Updated this week
- QA via natural language AI testsβ5,505Updated 5 months ago
- βοΈ Create and run workflows (RPA 2.0)β3,876Updated last week
- π₯ Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web witβ¦β6,322Updated last week
- A research prototype of a human-centered web agentβ9,632Updated 2 weeks ago
- Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent π€β7,604Updated this week
- A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.β5,370Updated 4 months ago
- Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerizβ¦β10,379Updated 4 months ago
- Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI asβ¦β10,302Updated last month
- Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.aiβ4,850Updated 3 weeks ago
- screenpipe turns your computer into a personal AI that knows everything you've done. record. search. automate. all local, all private, alβ¦β16,679Updated this week
- Allow LLMs to control a browser with Browserbase and Stagehandβ3,112Updated 2 weeks ago
- The Cursor for Designers β’ An Open-Source AI-First Design tool β’ Visually build, style, and edit your React App with AIβ24,645Updated 2 weeks ago
- Automate browser based workflows with AIβ20,305Updated this week
- β¨ Turn websites into structured APIs & clean data pipelines in minutes β¨β14,208Updated this week
- Task-Aware Agent-driven Prompt Optimization Frameworkβ3,753Updated 3 months ago