Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves

Open-source adapter between multimodal models and desktop/web GUIs. Record a workflow once, then compile it into a deterministic, self-healing replay (openadapt-flow) — or condition, train, and evaluate agents on it. Modular meta-package; install only the extras you need.

OmniMCP uses Microsoft OmniParser and Model Context Protocol (MCP) to provide AI models with rich UI context and powerful interaction capabilities.

AI agent that controls a computer

AI-powered computer control for automated testing. Factifai uses vision models (Claude, GPT-4o, Gemini) to interact with applications naturally - clicking, typing, and verifying results just like a human would.

Cappuccino is an GUI Agent based on desktop screen. It is a Manus-like AI Agent that can be deployed locally.

🤖 deploy OmniParser v2 model on Amazon SageMaker with async inference endpoint

Docker implementation of the OmniParser screen parsing tool

🤖 Control your Gemini computer effortlessly with a unified console for browser automation, desktop management, and intelligent task execution.

Effortless Deployment and Integration for SOTA Screenshot Parsing and Action Models

Working self-hosted version of Microsoft's OmniParser Image-to-text model, up-to-date with fixed dependency/compatibility issues and Fly GPU deployment.

Placeholder for Omniparser Schemas used by universal-etl-parser

A production-grade, voice-controlled multi-agent AI backend that autonomously controls Android devices using natural language. Runs a full perceive-decide-act-verify loop via 9 specialized agents, LangGraph orchestration, OmniParser hybrid perception, and reactive hybrid planning on real Android hardware.

macOS computer control CLI for AI agents & OpenClaw — control any app on your Mac using natural language labels. Powered by OmniParser v2 (YOLOv8 + Florence-2). Click, type, scroll, screenshot & automate anything.

A local Model Context Protocol server that gives any MCP-compatible agent host (Claude Desktop, Claude Code, Cursor, Cline, Continue, …) full computer-use capabilities on the host machine.

AI Chrome extension that captures pages, parses UI with OmniParser, plans actions with Claude, and executes click/type/scroll tasks.

Multi-format data transformation library for Go. Transform between JSON, CSV, EDI, XML, and text using schema-driven configurations.

AI-driven UI consistency testing pipeline — OmniParser → NMS → CLIP semantic matching → multi-model consensus. FastAPI + Docker + WebSocket

Generic, self-healing AI-driven web UI automation framework in Go. Multi-tier model routing (heuristics, LLM discovery, VLM verification), CDP/chromedp browser, OmniParser visual grounding, NL scenario runner, and full visual observability.