Skip to content

@OpenAdaptAI OpenAdapt.AI

Change the repository type filter

All

    Repositories list

    46 repositories

    • openadapt-capture

      Public
      GUI interaction capture -- production-ready event streams with time-aligned media
      pythonscreen-capturegui-automationinput-recordingopenadapt
      Python
      •0•2•0•1•Updated Feb 6, 2026Feb 6, 2026

    • openadapt-evals

      Public
      Evaluation infrastructure for GUI agent benchmarks
      pythonevaluationbenchmarksgui-automationopenadapt
      Python
      •
      MIT License
      •0•0•3•0•Updated Feb 6, 2026Feb 6, 2026

    • openadapt-ml

      Public
      OpenAdapt’s open-source ML toolkit for training and evaluating general multimodal GUI-action models.
      pythonmachine-learningvlmgui-automationcomputer-useopenadapt
      Python
      •
      MIT License
      •0•2•1•1•Updated Feb 6, 2026Feb 6, 2026

    • openadapt-retrieval

      Public
      Multimodal demo retrieval for GUI automation
      pythonretrievalembeddingsopenadaptdemo-retrieval
      Python
      •
      MIT License
      •0•0•0•0•Updated Jan 29, 2026Jan 29, 2026

    • openadapt-grounding

      Public
      Temporal smoothing for UI element detection with OmniParser integration
      pythoncomputer-visionui-detectionset-of-markopenadapt
      Python
      •
      MIT License
      •0•0•0•0•Updated Jan 29, 2026Jan 29, 2026

    • openadapt-privacy

      Public
      PII/PHI detection and redaction for GUI automation data (text, images, dicts)
      pythonprivacyscrubbingpii-detectionopenadapt
      Python
      •2•1•0•0•Updated Jan 29, 2026Jan 29, 2026

    • openadapt-viewer

      Public
      HTML viewer components for ML dashboards and benchmarks
      visualizationpythonhtmlopenadapt
      Python
      •
      MIT License
      •0•0•0•0•Updated Jan 29, 2026Jan 29, 2026

    • openadapt-tray

      Public
      System tray application for OpenAdapt
      Python
      •0•0•1•0•Updated Jan 29, 2026Jan 29, 2026

    • openadapt-web

      Public
      JavaScript
      •12•7•5•2•Updated Jan 29, 2026Jan 29, 2026

    • openadapt-bootstrap

      Public
      Self-hosting infrastructure for OpenAdapt recursive development
      Python
      •
      MIT License
      •0•0•5•0•Updated Jan 18, 2026Jan 18, 2026

    • .github

      Public
      0•0•0•0•Updated Jan 18, 2026Jan 18, 2026

    • OpenAdapt

      Public
      Open Source Generative Process Automation (i.e. Generative RPA). AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] /…
      pythontransformersopenaiagentsprocess-miningai-agentsprocess-automationhuggingfaceultralyticslarge-language-models
      Python
      •
      MIT License
      •217•1.5k•0•0•Updated Jan 17, 2026Jan 17, 2026

    • openadapt-agent

      Public
      Production execution engine for OpenAdapt GUI automation agents. Wraps trained models with safety gates, human-in-the-loop confirmation, session management, and…
      Python
      •
      MIT License
      •0•0•0•0•Updated Jan 17, 2026Jan 17, 2026

    • openadapt-telemetry

      Public
      Unified error tracking and usage analytics for OpenAdapt packages. GlitchTip/Sentry SDK integration with privacy filtering (PII scrubbing, path sanitization), o…
      Python
      •
      MIT License
      •0•0•0•0•Updated Jan 17, 2026Jan 17, 2026

    • OpenCUA

      Public
      OpenCUA: Open Foundations for Computer-Use Agents
      Python
      •
      MIT License
      •86•1•0•0•Updated Aug 18, 2025Aug 18, 2025

    • OmniMCP

      Public
      OmniMCP uses Microsoft OmniParser and Model Context Protocol (MCP) to provide AI models with rich UI context and powerful interaction capabilities.
      awsgeminiopenaigenerative-aianthropicomniparsercomputerusemodel-context-protocol
      Python
      •15•69•12•4•Updated Apr 8, 2025Apr 8, 2025

    • PydanticPrompt

      Public
      A simple library to document Pydantic models for structured LLM outputs using standard Python docstrings.
      Python
      •
      MIT License
      •0•6•0•1•Updated Apr 6, 2025Apr 6, 2025

    • OmniMCP.web

      Public archive
      Web interface for OmniMCP.
      JavaScript
      •12•0•0•0•Updated Mar 22, 2025Mar 22, 2025

    • OpenAdapter

      Public archive
      Effortless Deployment and Integration for SOTA Screenshot Parsing and Action Models
      pythonawsopenaigradiogithub-actionshuggingfaceanthropic-claudeomniparsercomputer-use
      0•1•3•1•Updated Feb 18, 2025Feb 18, 2025

    • OmniParser

      Public
      Jupyter Notebook
      •
      Creative Commons Attribution 4.0 International
      •2.1k•4•1•1•Updated Feb 14, 2025Feb 14, 2025

    • R1-V

      Public archive
      Witness the aha moment of VLM with less than $3.
      Python
      •287•0•0•0•Updated Feb 4, 2025Feb 4, 2025

    • Qwen2.5-VL

      Public archive
      Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
      Jupyter Notebook
      •
      Apache License 2.0
      •1.6k•0•0•0•Updated Jan 28, 2025Jan 28, 2025

    • open-r1-multimodal

      Public archive
      A fork to add multimodal model training to open-r1
      Python
      •
      Apache License 2.0
      •70•0•0•0•Updated Jan 28, 2025Jan 28, 2025

    • Janus

      Public archive
      Janus-Series: Unified Multimodal Understanding and Generation Models
      Python
      •
      MIT License
      •2.2k•0•0•0•Updated Jan 27, 2025Jan 27, 2025

    • UI-TARS-desktop

      Public
      An GUI Agent application based on UI-TARS(Vision-Lanuage Model) that allows you to control your computer using natural language.
      TypeScript
      •
      Apache License 2.0
      •2.7k•1•0•0•Updated Jan 21, 2025Jan 21, 2025

    • app

      Public archive
      A desktop application that enables end-users to automate their workflows with OpenAdapt
      MIT License
      •3•0•0•0•Updated Jan 11, 2025Jan 11, 2025

    • omniparser-api

      Public archive
      Self-hosted version of Microsoft's OmniParser Image-to-text model
      Python
      •24•0•0•0•Updated Nov 26, 2024Nov 26, 2024

    • OpenReflector

      Public
      OpenReflector links the Anthropic Computer Use container to a Windows or Mac desktop, using OpenAdapt and WebSockets for real-time, two-way mirroring of actions…
      MIT License
      •0•2•0•0•Updated Oct 31, 2024Oct 31, 2024

    • OpenSanitizer

      Public
      A privacy-focused module for detecting and scrubbing PII/PHI from screen data and user actions.
      MIT License
      •0•5•0•0•Updated Oct 31, 2024Oct 31, 2024

    • OpenAdaptVault

      Public archive
      Archival snapshot of OpenAdapt: Open Source Generative Process Automation (Generative RPA) with foundational AI models ([Language (LLMs) / Action (LAMs) / Multi…
      Python
      •
      MIT License
      •217•2•0•0•Updated Oct 30, 2024Oct 30, 2024