15 projects
openadapt-evals
Evaluation infrastructure for GUI agent benchmarks
openadapt-types
Canonical Pydantic schemas for computer-use agents: ComputerState, Action, ActionResult, UINode
openadapt-telemetry
Unified telemetry and error tracking for OpenAdapt packages
openadapt-ml
Model-agnostic, domain-agnostic ML engine for GUI automation agents
openadapt-capture
GUI interaction capture - platform-agnostic event streams with time-aligned media
openadapt-desktop
Cross-platform desktop app for continuous screen recording and AI training data collection
openadapt
GUI automation with ML - record, train, deploy, evaluate
openadapt-consilium
Multi-LLM council for consensus-driven AI responses
openadapt-retrieval
Multimodal demo retrieval using VLM embeddings for GUI automation
openadapt-grounding
Robust UI element localization for automation
openadapt-privacy
Privacy scrubbing for GUI automation data - PII/PHI detection and redaction
openadapt-viewer
Standalone HTML viewer generation for OpenAdapt ML dashboards and benchmarks
openadapt-tray
System tray application for OpenAdapt
pydantic-prompt
Document Pydantic models for structured LLM outputs using Python docstrings
oa-whisper
Robust Speech Recognition via Large-Scale Weak Supervision
