# OpenAdaptAI/OpenAdapt

Compile a demonstrated GUI workflow into a deterministic, locally executable program. Zero model calls on healthy runs; governed repair; halts instead of guessing. Launcher for openadapt-flow: pip install openadapt

Repository: https://github.com/OpenAdaptAI/OpenAdapt
Canonical: https://ross.abutalabs.com/products/openadapt
Homepage: https://www.OpenAdapt.AI
Language: Python
License: MIT
License Family: permissive
Topics: process-automation, python, agents, ai-agents, computer-use, computer-use-agents, desktop-automation, gui-automation, local-first, workflow-automation, browser-automation, citrix, deterministic-replay, effect-verification, healthcare-automation, rdp, rpa, ui-automation, demonstration-compiler, automation-from-demonstration
Last push: 2026-08-26T20:06:30+00:00

## Health v2 (maintenance only)
Score: 97/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 88
- inputs: {"age_days": 1239, "days_push": 7, "days_rel": 7, "gap_med": 0.5, "n_releases_24m": 57}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1702, forks 263 (observed 2026-08-28T04:05:24.387231+00:00)

## What it is
OpenAdapt is a Python framework that compiles a demonstrated GUI workflow into an inspectable, deterministic, locally executable program for browser, desktop, RDP, or Citrix/VDI surfaces. Healthy runs make zero generative-model calls, verify declared results before reporting success, and halt with evidence instead of guessing when verification fails.

## Use cases
- automate repetitive data entry into legacy desktop apps with no API
- record a GUI task once and replay it deterministically
- automate workflows over RDP or Citrix virtual desktops
- verify that automated browser actions actually produced the expected result
- automate patient data entry in healthcare systems with audit evidence
- replace manual RPA scripting by demonstrating the task instead of coding it

## When to choose
- the task is repeated GUI work on an application with no practical write API
- you need proof that each consequential step succeeded before reporting success
- you want local-first, MIT-licensed automation with no model calls on healthy runs
- a wrong action has operational, financial, or compliance cost and halting is preferable to guessing

## When to avoid
- you need fully autonomous agents that improvise novel UI interactions
- the workflow has no stable, demonstrable structure or changes constantly
- you only need simple API-to-API integration without any GUI surface
- you require a production-admitted, qualified deployment today (admission state is currently not actively admitted)

## Facets
- artifact type: framework
- maturity: active
- function: workflow-automation, agent-framework, computer-vision, gui, testing
- domain: developer-tools, healthcare, self-hosted
- platform: python, cross-platform, windows, cli, self-hosted
- tags: rpa, gui-automation, desktop-automation, browser-automation, computer-use-agents, deterministic-replay, automation-from-demonstration, rdp, citrix, process-automation, verification, local-first, automation, macos, linux

## Member repositories
- OpenAdaptAI/OpenAdapt (main) score 97

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.387231+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:37:39.367453+00:00, confidence not recorded.
  - readme: https://github.com/OpenAdaptAI/OpenAdapt (fetched 2026-08-28T04:05:24.387231+00:00, sha eb3183623c0e)
  - homepage: https://www.OpenAdapt.AI (fetched 2026-08-29T11:12:12.496720+00:00, sha e44669bd711a)
  - site_page: https://docs.openadapt.ai (fetched 2026-08-29T11:12:12.501506+00:00, sha 16b3b8612dfc)
  - site_page: https://openadapt.ai/about (fetched 2026-08-29T11:12:12.503249+00:00, sha a081a3fbe3df)
  - registry_pypi: https://pypi.org/pypi/openadapt/json (fetched 2026-08-29T11:12:12.504723+00:00, sha 5d9f3295e802)
  - site_page: https://openadapt.ai/pricing (fetched 2026-08-29T11:12:12.499638+00:00, sha 36a8972fee92)
- Data as of 2026-08-30T08:39:29.467469+00:00.