OpenAdapt.AI
OpenAdapt.AI is an open-sourceGenerative Process Automation framework that aims to transform task automation across applications and platforms. Designed as a baseline for evaluating agents, OpenAdapt.AI learns from human demonstrations to intelligently automate tasks, adapting dynamically to evolving workflows.
OpenAdapt.AI leverages advanced machine learning models to:
- Observe and Learn: Automatically learns from user interactions to generate automation scripts.
- Automate Intelligently: Adapts to software changes, varying workflows, and complex environments.
- Ensure Privacy: Privacy is a core focus, with robust data handling mechanisms to protect user data.
- Generative Process Automation: Automates tasks using generative AI models that learn from demonstrations.
- Cross-Platform Compatibility: Works seamlessly with browser apps (e.g., Chrome) and desktop applications.
- Audio Narration Transcription: Converts spoken instructions or feedback into automation scripts.
- Flexible LLM Model Providers: Supports multiple language model providers, including:
- Online:OpenAI,Anthropic,Google
- Offline (Work in Progress):Ollama,vLLM
- Open Source: Developed transparently and collaboratively by the community.
- Privacy by Design: Uses tools like AWS Rekognition, Microsoft Presidio, and Private-ai.com to ensure data privacy.
To get started with OpenAdapt.AI:
- Clone the Repository:
git clone https://github.com/OpenAdaptAI/OpenAdapt - Install Dependencies: Follow theInstallation Guide
- Run Your First Automation: Check out ourQuick Start Guide
We welcome contributions from everyone. Whether you're a developer, data scientist, tester, or just passionate about automation, there's a place for you here!
Join ourCommunity to discuss new ideas, report bugs, or seek help.
Looking to implement OpenAdapt.AI in your organization or need help tailoring it to your specific use case? We offer expert consulting services to assist with deployment, customization, and optimization of OpenAdapt.AI for your unique needs.
For more information or to schedule a consultation, contact us atsales@openadapt.ai.
OpenAdapt.AI is made possible by the support of our contributors and partners. If you're interested in sponsoring the development, check out ourGitHub Sponsors page.
For general questions, feedback, or partnership inquiries, please reach out atcontact@openadapt.ai.
OpenAdapt.AI is currently in alpha. While it's functional, some features are still under development. Use with caution in production environments.
PinnedLoading
Repositories
- OpenAdapt Public
Open Source Generative Process Automation (i.e. Generative RPA). AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models
OpenAdaptAI/OpenAdapt’s past year of commit activity - OpenAdapter Public
Effortless Deployment and Integration for SOTA Screenshot Parsing and Action Models
OpenAdaptAI/OpenAdapter’s past year of commit activity - Qwen2.5-VL Public Forked fromQwenLM/Qwen2.5-VL
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
OpenAdaptAI/Qwen2.5-VL’s past year of commit activity - open-r1-multimodal Public Forked fromEvolvingLMMs-Lab/open-r1-multimodal
A fork to add multimodal model training to open-r1
OpenAdaptAI/open-r1-multimodal’s past year of commit activity - Janus Public Forked fromdeepseek-ai/Janus
Janus-Series: Unified Multimodal Understanding and Generation Models
OpenAdaptAI/Janus’s past year of commit activity - UI-TARS-desktop Public Forked frombytedance/UI-TARS-desktop
An GUI Agent application based on UI-TARS(Vision-Lanuage Model) that allows you to control your computer using natural language.
OpenAdaptAI/UI-TARS-desktop’s past year of commit activity