OpenAdapt
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
Automating desktop and web GUI work by recording human demonstrations, where models fail on ambiguous interface affordances rather than on capability.
You cannot record demonstrations of the task; the approach conditions the agent on them rather than on prompting alone.
About OpenAdapt
OpenAdapt is the open source software adapter between Large Multimodal Models (LMMs) and traditional desktop and web GUIs.
OpenAdapt v1.0+ uses a modular meta-package architecture. The main openadapt package provides a unified CLI and depends on focused sub-packages via PyPI:
Zero-shot VLMs fail on GUI tasks not due to lack of capability, but due to ambiguity in UI affordances. OpenAdapt resolves this by conditioning agents on human demonstrations — "show, don't tell."
OpenAdapt is listed in this index written primarily in Python, with 1.9k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.
pip install openadapt # Minimal CLI only