ghostwright/ghost-os

Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required. observed · 2026-08-28

github.com/ghostwright/ghost-os · homepage · Swift · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

61/100

Activity 73
Release rhythm 74
Longevity 13

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

gap_med: 0.0
age_days: 195
days_rel: 174
days_push: 163
n_releases_24m: 9

Full methodology

Adoption not part of the score

1646 stars · 158 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Ghost OS is a native macOS framework that gives AI agents full computer-use capabilities by exposing the macOS accessibility tree, Chrome DevTools Protocol, an on-device vision model, and synthetic input through an MCP-compatible interface. It includes self-learning recipes that record a user performing a task once and replay it, letting agents click buttons, fill forms, and operate any app without screenshots.

Use cases

let an AI agent click buttons and fill forms in native macOS apps
automate sending emails or organizing files via an LLM agent
record a workflow once and have the agent replay it forever
give Claude Code or other MCP clients control of the Mac UI
control web apps through Chrome DevTools Protocol instead of screenshots
run on-device visual grounding when accessibility data is unavailable

When to choose

you need computer-use automation on macOS without screenshot-based vision loops
you want an MCP server that exposes native app control to any agent
you want fast, structured UI interaction via the accessibility tree
you want self-learning recorded workflows
you prefer on-device inference on Apple Silicon

When to avoid

you need computer-use on Linux or Windows
your automation is browser-only and a browser automation tool suffices
you need a screenshot-pixel-based approach for non-native rendering environments
you cannot grant macOS accessibility and input permissions

Facets

framework · maturity active

agent-framework mcp workflow-automation computer-vision gui operating-systems accessibility developer-tools cli computer-use accessibility-tree mcp-server self-learning-recipes apple-silicon cg-event chrome-devtools-protocol on-device-llm ai-agents automation macos swift

2 sources

readme: https://github.com/ghostwright/ghost-os · fetched 2026-08-28 · f933d76ede39
homepage: https://ghostwright.dev/ghost-os · fetched 2026-08-29 · 3bbb122749ec

Member repositories

Repository	Role	Health v2
ghostwright/ghost-os	main	61

For agents

markdown · JSON · MCP: product_card(name="ghostwright/ghost-os")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem