18 projects
openadapt-flow
Compile demonstrated GUI workflows into deterministic local replay with governed repair and refusal
openadapt-agent
Let your AI agent enter information in apps with no API and get back whether it saved (MCP and Agent Skills)
openadapt-verify
Verify an agent's writes through an independent system-of-record read path
openadapt-desktop
The OpenAdapt desktop app and local engine: record a data-entry task, run it on a list, and check each saved record
openadapt
Enters approved information into the apps your team already uses, checks that it saved, and stops for a person when something doesn't match.
openadapt-types
Pydantic models for computer-use agents: screen state (ComputerState, UINode), actions (Action), and results (ActionResult)
openadapt-privacy
Find and redact personal and health data in GUI recordings: typed text, accessibility trees, and screenshots
openadapt-capture
Record desktop mouse, keyboard, and screen activity, then load it from Python
openadapt-evals
Evaluation infrastructure for GUI agent benchmarks
openadapt-ml
Model-agnostic, domain-agnostic ML engine for GUI automation agents
openadapt-tray
Menu-bar and system-tray controls and status for OpenAdapt Desktop
openadapt-consilium
Multi-LLM council for consensus-driven AI responses
openadapt-telemetry
Unified telemetry and error tracking for OpenAdapt packages
openadapt-retrieval
Multimodal demo retrieval using VLM embeddings for GUI automation
openadapt-grounding
Robust UI element localization for automation
openadapt-viewer
Standalone HTML viewer generation for OpenAdapt ML dashboards and benchmarks
pydantic-prompt
Document Pydantic models for structured LLM outputs using Python docstrings
oa-whisper
Robust Speech Recognition via Large-Scale Weak Supervision